Ollama

Summary

Ollama is an open-source command-line tool for downloading and running large language models on your own machine instead of calling a hosted API. It installs on macOS, Windows, or Linux (or as a Docker image), and once running it exposes a REST API and Python/JS libraries so applications can talk to local models the same way they would talk to a cloud provider. It's aimed at developers building or testing AI-backed applications, and increasingly at coding workflows: it can launch and manage integrations like Claude Code, Codex, Copilot CLI, and OpenCode, and connect models to assistants such as OpenClaw across chat apps. It sits in the local-inference space, letting teams run models like Gemma 4 or Nemotron-3-Ultra without sending data off-device. Started in 2023, it now has 642 contributors and a release roughly every week, most recently 17 days ago.

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Command line

Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.

Release history

1. v0.33.1 Aug 26, 2026 · issue 009

   Ollama v0.33.1 adds structured output and Qwen3.8 Flash Next on the MLXMLXA Python machine-learning array framework made by Apple, designed for Apple Silicon, that gives cyber tools fast on-device model inference without needing a GPU separate from the CPU. backend, plus OLLAMA_HOST-aware Pi configuration.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.33.1 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.33.1

   • ›Adds structured output support to the MLX runner, enabling constrained-format responses on Apple Silicon via the MLX backend.
   • ›Adds support for the Qwen3.8 Flash Next model on the MLX backend.
2. v0.33.0 Aug 21, 2026 · issue 008

   Ollama v0.33.0 adds Claude Desktop integration, an 'Apps' connect experience, and smarter KV-cache-preserving prefill restore points.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.33.0 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.33.0

   
   └──▷ TRY IT
   Launch the Claude Code integration through Ollama to use a local model in place of Anthropic's API.
   copy

   $ ollama launch claude

   • ›Adds Claude Desktop integration on macOS: connect Ollama as a third-party gateway so Claude Desktop can use local Ollama models, with model selection, auto-mode, and install assistance from the menu bar.
   • ›Disables Claude Code's 'tokens left' token-countdown system message injection to preserve the KV cache across requests.
3. v0.32.15 Aug 19, 2026 · issue 003

   Ollama v0.32.15 adds a desktop onboarding flow and a model metadata cache that cuts time-to-first-token roughly in half.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.32.15 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.32.15

   • ›Adds a new desktop onboarding flow on first launch, guiding users through sign-in, local-only, or skip options before presenting the ollama command.
4. v0.32.14 Aug 15, 2026 · issue -004

   Ollama v0.32.14 adds WebP image support and more flexible system message placement for Qwen models.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.32.14 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.32.14

   • ›Adds WebP image transcoding for llama-server, enabling WebP inputs to be used in multimodal prompts.
   • ›Qwen renderer now tolerates system messages in non-leading positions, allowing more flexible conversation structures.
5. v0.32.14 Aug 15, 2026 · issue 001

   Ollama v0.32.14 adds WebP image transcoding and robust Qwen system-message handling.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.32.14 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.32.14

   • ›Automatically transcodes WebP image payloads to PNG before forwarding to llama-server, enabling vision model requests with WebP inputs (previously unsupported).
   • ›Qwen renderer now passes non-leading system messages through the raw ChatML path instead of returning an HTTP 500, supporting coding clients that inject runtime system prompts mid-conversation.
6. v0.32.13 Aug 14, 2026 · issue 001

   Ollama v0.32.13 adds Qwen3.8 model support including developer instructions and OpenAI-compatible agent compatibility.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.32.13 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.32.13

   • ›Adds Qwen3.8 model support with a dedicated renderer handling reasoning-effort and preserved-thinking chat template semantics.
   • ›Supports developer-role instructions for Qwen3.8, folding leading system/developer prefixes into a single system turn so OpenAI-compatible coding agents (which commonly send developer role messages) work without modification.
7. v0.32.13 Aug 14, 2026 · issue -005

   Ollama v0.32.13 adds Qwen3.8 model support including developer instructions and OpenAI-compatible agent compatibility.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.32.13 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.32.13

   • ›Adds Qwen3.8 model support with a dedicated renderer handling reasoning-effort and preserved-thinking chat template semantics.
   • ›Supports developer-role instructions for Qwen3.8, folding leading system/developer prefixes into a single system turn so OpenAI-compatible coding agents (which commonly send developer role messages) work without modification.
8. v0.32.12 Aug 14, 2026 · issue -005

   Ollama v0.32.12 adds Qwen3.8 27B support with an Apple Silicon MLX-optimized variant.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.32.12 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.32.12

   └──▷ TRY IT
   Run the Qwen3.8 27B model locally for coding or agentic tasks.
   copy

   $ ollama run qwen3.8:27b

   Run the Apple Silicon-optimized MLX variant of Qwen3.8 27B for faster inference on Mac.
   copy

   $ ollama run qwen3.8:27b-mlx

   • ›Adds qwen3.8:27b model, runnable via ollama run qwen3.8:27b, targeting coding, professional work, research, and long-horizon agentic tasks.
   • ›Adds qwen3.8:27b-mlx, an Apple Silicon-optimized MLX variant of Qwen3.8 27B, tuned for maximum performance and output quality in repeated tasks and coding agents.
9. v0.32.12 Aug 14, 2026 · issue 001

   Ollama v0.32.12 adds Qwen3.8 27B support with an Apple Silicon MLX-optimized variant.

   └──▷ GET THIS VERSION
   copy

   $ git clone --branch v0.32.12 https://github.com/ollama/ollama.git
   # already have the repo? check out this version:
   $ git checkout v0.32.12

   └──▷ TRY IT
   Run Qwen3.8 27B on Apple Silicon with the MLX-optimized variant for better throughput in coding-agent workflows.
   copy

   $ ollama run qwen3.8:27b-mlx

   Pull and chat with Qwen3.8 27B on any platform for long-horizon agentic or research tasks.
   copy

   $ ollama run qwen3.8:27b

   • ›Adds qwen3.8:27b-mlx model tag, an MLX-optimized build of Qwen3.8 27B tuned for maximum performance and output quality on Apple Silicon devices.
   • ›Adds qwen3.8:27b model to the Ollama library, bringing Qwen3.8 27B capabilities for coding, professional work, research, and long-horizon agentic tasks.
10. v0.32.11 Aug 14, 2026 · issue -005

    Ollama v0.32.11 adds DeepSeek Harness and Meta Muse Code support, plus web search in the Responses API.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.11 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.11

    └──▷ TRY IT
    Launch the DeepSeek agent harness locally to run agentic workflows powered by DeepSeek.
    copy

    $ ollama launch dsh

    Launch Meta's Muse Code agentic coding CLI via Ollama for local AI-assisted development.
    copy

    $ ollama launch muse

    • ›Adds ollama launch dsh support for DeepSeek Harness, DeepSeek's open-source agent harness.
    • ›Adds ollama launch muse support for Muse Code, Meta's agentic coding CLI.
    • ›The OpenAI-compatible Responses API now supports web search.
11. v0.32.11 Aug 14, 2026 · issue 001

    Ollama v0.32.11 adds DeepSeek Harness and Muse Code launch integrations plus web search in the OpenAI Responses API.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.11 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.11

    └──▷ TRY IT
    Launch DeepSeek Harness as a local agentic coding environment backed by Ollama.
    copy

    $ ollama launch dsh

    Launch Meta's Muse Code agentic coding CLI through Ollama.
    copy

    $ ollama launch muse

    • ›Adds ollama launch dsh to launch DeepSeek Harness, DeepSeek's open-source agent harness.
    • ›Adds ollama launch muse to launch Muse Code, Meta's agentic coding CLI.
    • ›Adds support for the Nemotron 3.5 prompt layout, selecting the 3.5 parser and renderer from its checkpoint template.
12. v0.32.9 Aug 11, 2026 · issue -008

    Ollama v0.32.9 adds NVIDIA Nemotron 3.5 Lightning, a 30B MoE model with 3B active parameters for always-on agents.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.9 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.9

    └──▷ TRY IT
    Run the new NVIDIA Nemotron 3.5 Lightning model locally for always-on agent workloads.
    copy

    $ ollama run nemotron-3.5-lightning

    • ›Adds nemotron-3.5-lightning model support via ollama run nemotron-3.5-lightning — a 30B mixture-of-experts model with 3B active parameters designed for always-on agent harnesses.
    • ›Adds the Nemotron 3 model architecture to Ollama's backend, enabling the new model family.
13. v0.32.9 Aug 11, 2026 · issue 001

    Ollama v0.32.9 adds NVIDIA Nemotron 3.5 Lightning (30B MoE) with built-in speculative decoding and MLXMLXA Python machine-learning array framework made by Apple, designed for Apple Silicon, that gives cyber tools fast on-device model inference without needing a GPU separate from the CPU. support for Nemotron 3 Nano Omni.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.9 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.9

    └──▷ TRY IT
    Run the new 30B Nemotron 3.5 Lightning MoE model locally for always-on agent workloads.
    copy

    $ ollama run nemotron-3.5-lightning

    • ›Adds nemotron-3.5-lightning, a 30B mixture-of-experts model with 3B active parameters, runnable via ollama run nemotron-3.5-lightning.
    • ›Adds the Nemotron 3 architecture backend with MLX support for Nemotron 3 Nano Omni, including Mamba2/recurrent layers, MoE routing, and quantized NVFP4/MXFP8 expert paths.
    • ›Serves the Nemotron model's multi-token prediction head as a built-in self-draft speculator, enabling speculative decoding without a separate draft model.
14. v0.32.8 Aug 10, 2026 · issue -009

    Ollama v0.32.8 adds Muse Glimmer model support across NVIDIA, AMD, and additional platforms.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.8 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.8

    └──▷ TRY IT
    Pull and run Muse Glimmer locally for interactive coding-agent use.
    copy

    $ ollama run muse-glimmer

    Connect Muse Glimmer to Claude Code as its local model backend.
    copy

    $ ollama launch claude --model muse-glimmer

    • ›Adds muse-glimmer model support on NVIDIA, AMD, and additional platforms (Apple Silicon was supported since v0.32.7), enabling local coding-agent and long-running personal-assistant workloads.
    • ›Supports running muse-glimmer with ollama launch claude --model muse-glimmer to power Claude Code locally.
    • ›Supports running muse-glimmer with ollama launch pi --model muse-glimmer for a lighter-weight coding-agent workflow.
    • ›Supports running muse-glimmer with ollama launch openclaw --model muse-glimmer and ollama launch hermes --model muse-glimmer for personal-assistant frameworks.
15. v0.32.8 Aug 10, 2026 · issue 001

    Ollama v0.32.8 adds Muse Glimmer model support across NVIDIA, AMD, and additional platforms.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.8 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.8

    └──▷ TRY IT
    Run Muse Glimmer locally as the backend for Claude Code for a fully local coding agent.
    copy

    $ ollama launch claude --model muse-glimmer

    Power the OpenClaw personal assistant framework locally with Muse Glimmer across WhatsApp, Telegram, Slack, and Discord.
    copy

    $ ollama launch openclaw --model muse-glimmer

    • ›Adds muse-glimmer model, runnable via ollama run muse-glimmer, supporting coding agent integrations (Claude Code, Codex, Pi) and personal assistant frameworks (OpenClaw, Hermes) on all platforms including NVIDIA and AMD GPUs.
    • ›Adds ollama launch claude --model muse-glimmer to wire Muse Glimmer directly into Claude Code as a local backend.
    • ›Adds ollama launch openclaw --model muse-glimmer and ollama launch hermes --model muse-glimmer to power personal assistant frameworks locally with Muse Glimmer.
16. v0.32.7 Aug 10, 2026 · issue -009

    Ollama v0.32.7 adds Muse Glimmer 30B via MLX engine on Apple Silicon, with DFlash and image input support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.7 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.7

    └──▷ TRY IT
    Run the Muse Glimmer 30B model locally on Apple Silicon for multimodal or agent workloads.
    copy

    $ ollama run muse-glimmer:30b-mlx

    Wire Muse Glimmer into a local Claude Code coding-agent session using the new ollama launch subcommand.
    copy

    $ ollama launch claude --model muse-glimmer:30b-mlx

    Launch the OpenClaw personal-assistant framework backed by a local Muse Glimmer instance.
    copy

    $ ollama launch openclaw --model muse-glimmer:30b-mlx

    • ›Adds muse-glimmer:30b-mlx model tag, enabling ollama run muse-glimmer:30b-mlx to download and run the 30B multimodal Muse Glimmer model locally on Apple Silicon via Ollama's MLX engine.
    • ›Adds ollama launch subcommand to start coding agent and personal assistant frameworks (e.g. claude, pi, openclaw, hermes) directly against a local model via --model.
    • ›MLX engine on Apple Silicon gains DFlash support and image input for Muse Glimmer as of this release.
17. v0.32.7 Aug 10, 2026 · issue 001

    Ollama v0.32.7 adds Muse Glimmer 30B multimodal support with DFlash and image input on Apple Silicon MLXMLXA Python machine-learning array framework made by Apple, designed for Apple Silicon, that gives cyber tools fast on-device model inference without needing a GPU separate from the CPU. engine.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.7 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.7

    └──▷ TRY IT
    Run Muse Glimmer locally on Apple Silicon for direct chat or scripting via the REST API.
    copy

    $ ollama run muse-glimmer:30b-mlx

    Launch Claude Code backed by Muse Glimmer on Apple Silicon for a fully local coding agent.
    copy

    $ ollama launch claude --model muse-glimmer:30b-mlx

    Launch the OpenClaw personal assistant framework with Muse Glimmer for a local AI assistant across WhatsApp, Telegram, and more.
    copy

    $ ollama launch openclaw --model muse-glimmer:30b-mlx

    • ›Adds muse-glimmer:30b-mlx model tag, enabling ollama run muse-glimmer:30b-mlx to run Meta's Muse Glimmer 30B multimodal model locally via the MLX engine on Apple Silicon.
    • ›Adds ollama launch claude --model muse-glimmer:30b-mlx, ollama launch pi --model muse-glimmer:30b-mlx, ollama launch openclaw --model muse-glimmer:30b-mlx, and ollama launch hermes --model muse-glimmer:30b-mlx to wire Muse Glimmer into Claude Code, Pi, OpenClaw, and Hermes agent frameworks.
    • ›Adds DFlash block-diffusion draft model support to the MLX runner, enabling speculative decoding on Apple Silicon for Muse Glimmer.
    • ›Adds image input support to the MLX runner for Muse Glimmer (and Qwen3.5), enabling multimodal prompts on Apple Silicon.
    • ›Adds ctrl+o keyboard shortcut to the agent TUI to toggle completed thinking trace details inline.
    +2 moreshow less

    • ›Streams live thinking deltas in the agent TUI beneath a Thinking ↓ N tokens row, collapsing to a persistent Thought row when a response or tool call begins.
    • ›Expands namespace tool declarations in the OpenAI Responses API, unfolding nested tools arrays into namespace-qualified flat function names so namespaced tool calls are fully declared to the model.
18. v0.32.6 Aug 4, 2026 · issue -015

    Ollama v0.32.6 brings automatic speculative decoding for Qwen3.5 on Apple GPUs and OpenAI-compatible streaming fixes.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.6 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.6

    └──▷ TRY IT
    Stream a chat completion and receive token-usage statistics in a separate final chunk, matching OpenAI's format.
    copy

    $ curl http://localhost:11434/v1/chat/completions \
      -H 'Content-Type: application/json' \
      -d '{"model": "qwen3", "stream": true, "stream_options": {"include_usage": true}, "messages": [{"role": "user", "content": "Hello"}]}'

    Run a cloud-only Kimi K3 model that has no default local tag without hitting a failure.
    copy

    $ ollama run kimi-k3:cloud

    • ›Adds stream_options.include_usage support to /v1/chat/completions streaming, now matching OpenAI's wire format: role only on the first chunk, finish_reason on its own trailing chunk, and usage in a separate chunk.
    • ›Adds kimi-k3:cloud tag so ollama run kimi-k3 can pull cloud-only models that publish no default tag, instead of failing.
    • ›Qwen3.5 on Apple GPUs now automatically uses the model's MTP head for speculative decoding via the MLX engine, improving inference speed.
    └──▷ BREAKING ON UPGRADE

    • !Experimental image generation has been temporarily removed; users must continue using v0.32.5 for image generation support.
19. v0.32.6 Aug 4, 2026 · issue 001

    Ollama v0.32.6 adds OpenAI-compatible streaming, cloud-model fallback, and automatic speculative decoding for Qwen3.5 on Apple GPUs.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.6 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.6

    └──▷ TRY IT
    Consume a streaming OpenAI-compatible chat response with token-usage stats, now that stream_options.include_usage is supported.
    copy

    $ curl http://localhost:11434/v1/chat/completions \
      -H 'Content-Type: application/json' \
      -d '{
        "model": "qwen3.5",
        "stream": true,
        "stream_options": {"include_usage": true},
        "messages": [{"role": "user", "content": "Summarize the OWASP Top 10"}]
      }'

    • ›Adds stream_options.include_usage support to /v1/chat/completions streaming, now matching OpenAI's wire format: role only on the first chunk, finish_reason on its own trailing chunk, and usage in a separate chunk.
    • ›Truncated responses from /v1/chat/completions now correctly report finish_reason: "length" instead of "finish_reason: "tool_calls".
    • ›Qwen3.5 inference on Apple GPUs is faster: the MLX engine now automatically uses the model's MTP head for speculative decoding.
    • ›Experimental image generation has been removed; users needing it should remain on v0.32.5.
    └──▷ BREAKING ON UPGRADE

    • !Experimental image generation support is removed in v0.32.6. Workloads depending on it must stay on v0.32.5.
20. v0.32.4 Jul 25, 2026 · issue -025

    Ollama v0.32.4 adds Laguna Apple GPU support and improves speculative-decoding draft quantization.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.4

    • ›Adds support for the Laguna architecture on Apple GPUs via the MLX engine.
    • ›Quantizes draft-model output heads at the requested type when creating speculative-decoding drafts.
21. v0.32.4 Jul 25, 2026 · issue 001

    Ollama v0.32.4 adds Laguna MLX support with memory residency, smarter speculative-decoding quantization, and agent skill permissions.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.4

    • ›Quantizes draft-model output heads at the requested quantization type when creating speculative-decoding drafts, aligning draft and base model precision.
    • ›Adds permission/approval flow for model-initiated skill tool invocations in the agent TUI, while preserving direct user slash-skill activation without a prompt.
    • ›Adds /system prompt inspection and on/off toggle commands to the agent TUI, with cache-impact warning and completions while typing.
22. v0.32.3 Jul 23, 2026 · issue 001

    Ollama v0.32.3 adds CUDA on Windows ARM64, B200 GPU support, Laguna 2.1 model capabilities, and restored Claude Code Channels.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.3

    • ›Adds CUDA support on Windows ARM64, enabling GPU-accelerated inference on ARM-based Windows devices.
    • ›Adds B200 GPU support via CUDA 12 (compute capability 10.0 on Linux).
    • ›Reduces memory use on Linux CUDA and ROCm iGPUs through Direct I/O (dio) enablement.
    • ›Adds chat, thinking, and tool calling support for Laguna 2.1 models, including a Metal inference fix.
    • ›Updates the MLX and llama.cpp engines.
23. v0.32.3 Jul 23, 2026 · issue -027

    Ollama v0.32.3 adds CUDA on Windows ARM64, B200 GPU support, Laguna 2.1 model capabilities, and restored Claude Code Channels.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.3

    • ›Adds CUDA support on Windows ARM64, enabling GPU-accelerated inference on ARM-based Windows devices.
    • ›Adds B200 GPU support via CUDA 12 (compute capability 10.0 on Linux).
    • ›Reduces memory use on Linux CUDA and ROCm iGPUs through Direct I/O (dio) enablement.
    • ›Adds chat, thinking, and tool calling support for Laguna 2.1 models, including a Metal inference fix.
    • ›Updates the MLX and llama.cpp engines.
24. v0.32.1 Jul 16, 2026 · issue -034

    Ollama v0.32.1 improves Gemma 4 tool calling, MLX timeout support, and agent context awareness.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.1

    • ›MLX text model loading now respects the OLLAMA_LOAD_TIMEOUT environment variable, enabling timeout control for MLX backends.
    • ›The interactive agent now receives the current working directory, giving models better project context during sessions.
    • ›Agent web search and fetch now prompt users to run ollama signin when authentication is required.
    • ›Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations.
25. v0.32.0 Jul 11, 2026 · issue -039

    Ollama v0.32.0 launches an interactive agent experience and renames the ChatGPT integration.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.32.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.32.0

    └──▷ TRY IT
    Start the interactive agent session to chat, write code, or delegate tasks without specifying a subcommand.
    copy

    $ ollama

    Launch the renamed ChatGPT integration, or use --restore to revert to your previous ChatGPT profile.
    copy

    $ ollama launch chatgpt --restore

    • ›New interactive agent experience: running ollama with no arguments now launches an agent for coding, web search, and delegating work.
    • ›Simplified ollama launch menu now surfaces only the most popular integrations; all others remain accessible via ollama launch directly.
    • ›Adds deprecation warnings before launching older agent models (CodeLlama, Qwen2.5(-coder), Llama 3.x, Mistral, StarCoder, base DeepSeek-R1 tags).
26. v0.31.2 Jul 6, 2026 · issue -044

    Ollama v0.31.2 enables flash attention on older NVIDIA GPUs and iGPU vision model offloading.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.31.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.31.2

    • ›Enables flash attention on older NVIDIA GPUs with compute capability 6.x, unlocking faster inference on Pascal-generation hardware.
    • ›iGPU can now offload vision models with padding to fit available memory, expanding multimodal model support on integrated graphics.
    • ›ollama launch for Claude Code now disables telemetry by default.
27. v0.31.1 Jun 30, 2026 · issue -050

    Gemma 4 on Apple Silicon now generates tokens ~90% faster via automatic multi-token prediction (MTP) — no config needed.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.31.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.31.1

    • ›Enables multi-token prediction (MTP) for Gemma 4 on Apple Silicon, delivering ~90% faster token generation on average with no configuration or output changes.
28. v0.30.11 Jun 25, 2026 · issue -055

    Ollama v0.30.11 adds thinking capability detection, auto-install for Claude Code and opencode, and broader CUDA/GPU support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.11 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.11

    • ›Adds thinking capability detection for opencode integration.
    • ›Auto-installs Claude Code when missing, streamlining AI coding assistant setup.
    • ›Auto-installs opencode when missing, reducing manual setup steps.
    • ›Detects model drift when the Codex App UI switches models.
    • ›Adds sm_86 GPU architecture support to the CUDA v13 Windows preset.
    +5 moreshow less

    • ›Adds Compute Capability 87 (CC 87) support for CUDA v13 on Jetson devices.
    • ›Uses the host Vulkan loader on Windows for improved GPU compatibility.
    • ›Sizes multimodal projector (mmproj) offload based on projector memory.
    • ›Aligns the generate endpoint with native chat templates for more consistent output.
    • ›Unifies and tunes speculative decoding on the MLX runner.
29. v0.30.10 Jun 17, 2026 · issue -063

    Ollama v0.30.10 brings Command A and North family models to Apple Silicon via the MLX engine.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.10 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.10

    • ›Supports Command A and North family models running on Apple Silicon using the MLX engine.
30. v0.30.9 Jun 15, 2026 · issue -065

    Ollama v0.30.9 adds Cohere2Moe architecture support and context-window overflow error reporting.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.9 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.9

    • ›Supports the Cohere2Moe model architecture for running Cohere mixture-of-experts models locally.
    • ›Returns an error when a single message exceeds the current context window, enabling clearer failure handling in pipelines.
31. v0.30.7 Jun 7, 2026 · issue -073

    Ollama v0.30.7 adds ollama launch hermes-desktop for a native visual interface to the Hermes agent.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.7 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.7

    └──▷ TRY IT
    Launch a visual desktop interface alongside your Hermes agent to manage conversations and integrations without using the CLI for every interaction.
    copy

    $ ollama launch hermes-desktop

    • ›Adds ollama launch hermes-desktop to spin up Hermes Desktop, a native UI for managing Hermes agent conversations, integrations, and messaging apps.
    • ›OpenAI-compatible API models list now aligns with available model tags, improving API accuracy.
32. v0.30.6 Jun 5, 2026 · issue -075

    Ollama v0.30.6 adds Gemma 4 QAT models, Oh My Pi IDE agent integration, and improved Apple Silicon embedding quantization.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.6 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.6

    └──▷ TRY IT
    Launch an AI coding agent with IDE integration directly from the CLI.
    copy

    $ ollama launch omp

    Run a memory-efficient Gemma 4 QAT model locally when GPU VRAM is constrained.
    copy

    $ ollama run gemma4:12b-it-qat

    • ›Adds Gemma 4 QAT model variants (gemma4:*-qat tags) with quantization-aware training to reduce memory requirements and boost on-device performance.
    • ›New ollama launch omp command integrates with Oh My Pi, an AI coding agent with IDE integration.
    • ›MLX embedding layers now use NVFP4 global scale for improved quantization quality on Apple Silicon.
33. v0.30.5 Jun 4, 2026 · issue -076

    ollama launch hermes-desktop skips rebuilds on installed apps; native Windows support added for ollama launch hermes.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.5 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.5

    └──▷ TRY IT
    Launch Hermes Desktop on a machine where it's already installed, bypassing a slow rebuild step.
    copy

    $ ollama launch hermes-desktop

    Install and launch the Hermes assistant on a native Windows system using the PowerShell installer path.
    copy

    $ ollama launch hermes

    • ›Supports skipping rebuild in ollama launch hermes-desktop when a packaged desktop app is already installed.
    • ›Enables native Windows installs via the Hermes PowerShell installer with ollama launch hermes.
34. v0.30.4 Jun 3, 2026 · issue -077

    Ollama v0.30.4 adds NVIDIA Nemotron-3-Ultra and improves MLX Modelfile REQUIRES support for experimental model creation.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.4

    └──▷ TRY IT
    Pull and run NVIDIA's Nemotron-3-Ultra for agent or reasoning workloads.
    copy

    $ ollama run nemotron-3-ultra

    Create an MLX-based model that declares dependencies via REQUIRES in its Modelfile.
    copy

    $ ollama create --experimental my-mlx-model -f ./Modelfile

    • ›New model: Nemotron-3-Ultra, NVIDIA's model optimized for high-throughput reasoning and long-running agent workflows.
    • ›ollama create --experimental now respects the REQUIRES directive in Modelfiles for MLX-based models.
35. v0.30.3 Jun 3, 2026 · issue -077

    Ollama v0.30.3 adds support for running the Gemma 4 12B multimodal model locally.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.3

    └──▷ TRY IT
    Pull and run the new Gemma 4 12B multimodal model locally for reasoning or image tasks.
    copy

    $ ollama run gemma4:12b

    • ›Supports Gemma 4 12B, a multimodal model with advanced reasoning designed to run on consumer laptops.
36. v0.30.2 Jun 3, 2026 · issue -077

    Ollama v0.30.2 adds Qwen Code support, Laguna architecture backend, and Radeon 8060S GPU enablement.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.2

    └──▷ TRY IT
    Run Codex in an isolated configuration so it doesn't interfere with your existing Codex settings.
    copy

    $ ollama launch codex

    • ›Adds Qwen Code model support via ollama launch, including guided Cline CLI installation when missing.
    • ›Adds llama.cpp backend support for Poolside's Laguna model architecture.
    • ›Enables Radeon 8060S integrated GPUs by default.
    • ›Includes template details in logs to aid troubleshooting of model prompts.
    • ›llama.cpp backend now includes cached prompt tokens in token accounting, improving usage reporting for prompt-cache-hit requests.
37. v0.24.0 May 14, 2026 · issue -097

    Ollama v0.24 launches Codex App support with built-in browser, review mode, and reworked MLX sampler.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.24.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.24.0

    └──▷ TRY IT
    Launch the Codex App to work on coding tasks with parallel threads, worktree support, and git integration.
    copy

    $ ollama launch codex-app

    Roll back to a previous Codex App configuration after an upgrade.
    copy

    $ ollama launch codex-app --restore

    • ›Adds ollama launch codex-app to run OpenAI's Codex desktop experience with parallel thread support, built-in worktree management, and git functionality.
    • ›Codex App includes a built-in browser for loading local servers and annotating pages directly to request code changes.
    • ›Codex App includes a Review mode for leaving inline comments and iterating on code without leaving the workspace.
    • ›Supports ollama launch codex-app --restore to revert to a previous Codex App configuration.
    • ›Reworked MLX sampler improves generation quality on Apple Silicon.
38. v0.23.4 May 13, 2026 · issue -098

    ollama launch opencode now accepts image inputs when using vision models.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.23.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.23.4

    └──▷ TRY IT
    Use a vision model interactively with image inputs through the opencode launcher.
    copy

    $ ollama launch opencode

    • ›Enables image input support for vision models via ollama launch opencode.
39. v0.30.0 May 13, 2026 · issue -098

    Ollama v0.30.0 adds llama.cpp engine support, broader GGUF model compatibility, and faster NVIDIA performance.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.30.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.30.0

    • ›Adds llama.cpp engine as a backend, augmenting the existing MLX engine on Apple Silicon and extending support to a wider range of hardware.
    • ›Supports GGUF-based models from Hugging Face directly, including user fine-tuned models.
    • ›Delivers faster inference performance on NVIDIA hardware.
    └──▷ BREAKING ON UPGRADE

    • !nomic-embed-text now converts inputs to lowercase per the model card; prior Ollama versions incorrectly preserved mixed case, so embeddings generated by this model will differ from previous versions.
40. v0.23.2 May 7, 2026 · issue -104

    Ollama v0.23.2 caches /api/show for ~6.7x faster model-load latency and refines launch integration management.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.23.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.23.2

    └──▷ TRY IT
    Restore Claude Desktop to its default state after Ollama previously modified it via the launch integration.
    copy

    $ ollama launch claude-desktop --restore

    • ›Caches /api/show API responses, cutting median latency by ~6.7x and accelerating integrations such as VS Code.
    • ›Adds ollama launch claude-desktop --restore command to return Claude Desktop to its normal state after integration removal.
    • ›Improves backup workflow when managing ollama launch integrations.
    • ›Delivers a cleaner image-generation layout in the MLX runner.
    └──▷ BREAKING ON UPGRADE

    • !ollama launch no longer includes Claude Desktop; the third-party integration has been removed because it was limited to Anthropic models.
41. v0.23.1 May 5, 2026 · issue -106

    Ollama v0.23.1 adds Gemma 4 MTP speculative decoding on Mac, delivering 2x+ speed on 31B coding tasks.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.23.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.23.1

    └──▷ TRY IT
    Run Gemma 4 31B with speculative decoding on a Mac to get 2x+ faster completions on coding tasks.
    copy

    $ ollama run gemma4:31b-coding-mtp-bf16

    • ›Supports Gemma 4 MTP (Multi-token Processing) speculative decoding on Macs via the MLX runner, enabling 2x+ speed gains for the Gemma 4 31B model on coding tasks.
42. v0.23.0 May 3, 2026 · issue -108

    Ollama v0.23.0 adds ollama launch claude-desktop support and server-driven featured model recommendations.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.23.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.23.0

    └──▷ TRY IT
    Launch Claude Desktop with Cowork and Code support without leaving your Ollama workflow.
    copy

    $ ollama launch claude-desktop

    Use Claude Code in the terminal via the existing CLI entry point.
    copy

    $ ollama launch claude

    • ›Adds ollama launch claude-desktop to launch Claude Desktop (including Claude Cowork and Claude Code) directly from Ollama.
    • ›Surfaces featured models in the Ollama app via server-driven recommendations.
43. v0.22.1 Apr 28, 2026 · issue -113

    Ollama v0.22.1 updates the Gemma 4 renderer for thinking and tool calling, and decouples model recommendations from app updates.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.22.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.22.1

    • ›Updated Gemma 4 renderer with improved thinking and tool calling support.
    • ›Model recommendations now refresh independently, without requiring an Ollama update.
    • ›Aligns the desktop app's launch page with ollama launch integrations.
44. v0.22.0 Apr 28, 2026 · issue -113

    Ollama v0.22.0 adds NVIDIA Nemotron 3 Omni and Poolside Laguna XS.2 to the model library.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.22.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.22.0

    └──▷ TRY IT
    Pull and run Poolside's open-weight coding model to get inline code completions or explanations from the CLI.
    copy

    $ ollama run laguna-xs.2

    Pull and run NVIDIA's Nemotron 3 Omni model for multimodal tasks directly from the terminal.
    copy

    $ ollama run nemotron3

    • ›Adds NVIDIA Nemotron 3 Omni multimodal model via ollama run nemotron3.
    • ›Adds Poolside's Laguna XS.2, an open-weight coding-focused model, via ollama run laguna-xs.2.
45. v0.21.3-rc0 Apr 24, 2026 · issue -117

    Ollama v0.21.3-rc0 adds max as a think value and maps OpenAI reasoning effort to think parameter.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.3-rc0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.21.3-rc0

    └──▷ TRY IT
    Use maximum thinking depth when generating a response via the Ollama API.
    copy

    $ curl http://localhost:11434/api/generate -d '{"model": "qwq", "prompt": "Solve this step by step: ...", "think": "max"}'

    • ›Accepts "max" as a valid value for the think parameter, enabling maximum reasoning depth in a single flag.
    • ›Maps OpenAI Responses API reasoning_effort field to Ollama's think parameter, enabling OpenAI-compatible clients to control thinking mode.
46. v0.21.2 Apr 23, 2026 · issue -118

    Ollama v0.21.2 bundles web search in OpenClaw and stabilizes the ollama launch onboarding flow.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.21.2

    └──▷ TRY IT
    Launch the OpenClaw interface to get web search-augmented model responses immediately, with no additional plugin configuration.
    copy

    $ ollama launch

    • ›OpenClaw integration now includes Ollama's web search plugin out of the box, enabling web-augmented queries without manual plugin setup.
47. v0.21.1 Apr 22, 2026 · issue -119

    Ollama v0.21.1 adds Kimi CLI integration, logprobs support in MLX, and faster MLX sampling.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.21.1

    └──▷ TRY IT
    Run Kimi K2.6 as an agentic assistant for long-horizon tasks directly from the CLI.
    copy

    $ ollama launch kimi --model kimi-k2.6:cloud

    • ›New ollama launch command installs and runs the Kimi CLI, enabling long-horizon agentic execution via a multi-agent system with models like kimi-k2.6:cloud.
    • ›MLX runner now supports logprobs for compatible models.
    • ›Faster MLX sampling via fused top-P and top-K in a single sort pass, with repeat penalties applied in the sampler.
    • ›Improved MLX prompt tokenization by moving tokenization into request handler goroutines.
    • ›GLM4 MoE Lite gains a performance improvement with a fused sigmoid router head.
48. v0.21.0 Apr 16, 2026 · issue -125

    Ollama v0.21.0 adds Hermes Agent, GitHub Copilot CLI integration, and Gemma 4 on Apple Silicon MLX.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.21.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.21.0

    └──▷ TRY IT
    Launch the Hermes Agent to get an AI assistant that learns your workflows and builds skills over time.
    copy

    $ ollama launch hermes

    • ›Adds ollama launch hermes to run the Hermes Agent, which automatically creates skills to better serve research and engineering workflows.
    • ›Adds GitHub Copilot CLI as a supported integration in ollama launch, configurable alongside other coding agents in a single command.
    • ›Supports running Gemma 4 via the MLX backend on Apple Silicon, including a text-only MLX runtime.
    • ›Adds mixed-precision quantization to the MLX backend.
    • ›Expands MLX backend with new op wrappers: Conv2d, Pad, activations, trig, masked SDPA, and RoPE-with-freqs.
    +1 moreshow less

    • ›ollama launch opencode now writes config inline instead of to a separate file, consistent with other integrations.
49. v0.20.5 Apr 9, 2026 · issue -132

    Ollama v0.20.5 adds OpenClaw messaging-channel setup and flash attention for Gemma 4.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.20.5 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.20.5

    └──▷ TRY IT
    Spin up an OpenClaw instance to route WhatsApp, Telegram, or Discord traffic through a local Ollama model.
    copy

    $ ollama launch openclaw

    • ›New ollama launch openclaw command sets up OpenClaw channels, connecting WhatsApp, Telegram, Discord, and other messaging platforms.
    • ›Enables flash attention for Gemma 4 on compatible GPUs.
    • ›ollama launch opencode now auto-detects curl-based OpenCode installs at ~/.opencode/bin.
50. v0.20.3 Apr 7, 2026 · issue -134

    Ollama v0.20.3 adds latest models to the app and improves Gemma 4 tool calling support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.20.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.20.3

    • ›Adds latest models to the Ollama App model library.
    • ›Improves Gemma 4 tool calling capabilities.
51. v0.20.0 Apr 2, 2026 · issue -139

    Ollama v0.20.0 adds Google Gemma 4 model family support across four sizes including MoE and dense variants.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.20.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.20.0

    └──▷ TRY IT
    Run the lightweight Gemma 4 E2B model for fast, resource-efficient local inference.
    copy

    $ ollama run gemma4:e2b

    Run the Gemma 4 26B Mixture-of-Experts model for stronger reasoning while keeping active parameters low.
    copy

    $ ollama run gemma4:26b

    • ›Supports Google Gemma 4 models in four sizes: E2B, E4B, 26B (Mixture of Experts with 4B active parameters), and 31B (Dense).
    • ›Adds SentencePiece-style BPE tokenizer support.
52. v0.19.0 Mar 27, 2026 · issue -145

    Ollama v0.19.0 powers Apple Silicon with MLX backend and adds web search to ollama launch pi.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.19.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.19.0

    └──▷ TRY IT
    Run the Pi assistant with web search enabled to answer questions requiring live information.
    copy

    $ ollama launch pi

    • ›Adds MLX-powered inference backend for Apple Silicon, leveraging unified memory architecture for improved performance.
    • ›Adds web search plugin to ollama launch pi, using Ollama's built-in web search capability.
    • ›MLX runner now creates periodic snapshots during prompt processing, enabling more resilient long-context runs.
53. v0.18.3 Mar 25, 2026 · issue -147

    Ollama v0.18.3 adds direct VS Code integration via GitHub Copilot, letting local models be used inside the editor.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.18.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.18.3

    └──▷ HOW TO FIND IT
    Use a locally running Ollama model as your Copilot model inside VS Code without leaving the editor.
    📍In VS Code with GitHub Copilot, open the model picker in the Copilot chat panel and select any model served by your local Ollama instance.
    • ›Enables VS Code GitHub Copilot integration so any local or cloud Ollama model can be selected directly inside Visual Studio Code.
54. v0.18.1 Mar 17, 2026 · issue -155

    Ollama v0.18.1 adds web search/fetch for OpenClaw and headless mode for ollama launch.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.18.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.18.1

    └──▷ TRY IT
    Run a CI pipeline step that asks a cloud model to review a repository without any interactive prompts.
    copy

    $ ollama launch claude --model kimi-k2.5:cloud --yes -- -p "how does this repository work?"

    Add web search to an already-configured OpenClaw instance so models can retrieve live content during sessions.
    copy

    $ openclaw plugins install @ollama/openclaw-web-search

    Spin up OpenClaw with Ollama's official auth and model provider to enable web search and fetch in an interactive session.
    copy

    $ ollama launch openclaw

    • ›Adds web search and web fetch plugin for OpenClaw via ollama launch openclaw, enabling local and cloud models to retrieve and extract readable web content.
    • ›Supports installing the web search capability directly into an existing OpenClaw setup with openclaw plugins install @ollama/openclaw-web-search.
    • ›Adds non-interactive (headless) mode to ollama launch via --yes flag and required --model argument, enabling automated pipelines, CI/CD security checks, and scripted prompt evaluation.
    • ›Enables OpenClaw subagent task execution in headless mode for automated multi-step workflows.
55. v0.18.0 Mar 14, 2026 · issue -157

    Ollama v0.18 adds non-interactive launch support, Nemotron-3-Super, ROCm 7, and Ollama-as-OpenClaw provider

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.18.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.18.0

    └──▷ TRY IT
    Run an automated code review in a GitHub Actions workflow without any interactive prompts.
    copy

    $ ollama launch claude \
    	--model glm-5:cloud \
    	--yes \
    	-- "Do a quick code review of this pull request and respond on GitHub with a comment summarizing your feedback."

    Use Ollama as the auth and model provider when setting up OpenClaw, pointing it at NVIDIA's new Nemotron-3-Super cloud model.
    copy

    $ openclaw onboard \
    	--auth-choice ollama \
    	--custom-model-id nemotron-3-super:cloud

    Run Nemotron-3-Super via Ollama's cloud for agentic reasoning tasks without a local 96GB VRAM requirement.
    copy

    $ ollama run nemotron-3-super:cloud

    • ›Adds --yes flag to ollama launch for non-interactive/scripted use (GitHub Actions, CI pipelines, etc.)
    • ›Adds Nemotron-3-Super (122B) model with strong reasoning and tool calling, runnable via cloud tag or locally with 96GB+ VRAM
    • ›Ollama can now be selected as an authentication and model provider during OpenClaw onboarding
    • ›Cloud models (:cloud tag) no longer require ollama pull — they connect automatically
    • ›Ships with ROCm 7, bringing updated AMD GPU support
    +2 moreshow less

    • ›Up to 10x lower latency for MiniMax-M2.5 and up to 2x for Qwen3.5 on Ollama's cloud for North American customers
    • ›Up to 2x faster speeds with Kimi-K2.5 via OpenClaw
    └──▷ BREAKING ON UPGRADE

    • !ROCm 7 is now bundled; AMD GPU users must update drivers to the latest version for continued GPU support.
56. v0.17.8-rc4 Mar 10, 2026 · issue -161

    Ollama v0.17.8-rc4 adds MLX int4 groupsize 64 support and updates ROCm on Linux to v7.2.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.17.8-rc4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.17.8-rc4

    • ›Updates ROCm support on Linux to v7.2.
    • ›Adds MLX int4 groupsize 64 quantization support for Apple Silicon inference.
    • ›MLX runner now reads model parameters directly from the Modelfile during model creation.
    • ›Removes requirement to pull stubs for cloud models, streamlining cloud model usage.
57. v0.17.7 Mar 5, 2026 · issue -166

    Ollama v0.17.7 adds thinking-level support in the API and context-length compaction for ollama launch.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.17.7 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.17.7

    └──▷ TRY IT
    Control reasoning depth on a thinking model by passing a named thinking level through the API instead of a raw token budget.
    copy

    $ curl http://localhost:11434/api/chat -d '{"model": "qwq", "options": {"thinking": "medium"}, "messages": [{"role": "user", "content": "Explain RSA encryption."}]}'

    • ›Supports named thinking levels (e.g., "medium") for thinking models via Ollama's API.
    • ›Adds context-length parameter to enable compaction when using ollama launch.
58. v0.17.5 Mar 2, 2026 · issue -169

    Ollama v0.17.5 adds Qwen3.5 model support and peak memory visibility in the MLX engine.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.17.5 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.17.5

    └──▷ TRY IT
    Pull and run a small Qwen3.5 model while monitoring peak MLX memory usage during inference.
    copy

    $ ollama pull qwen3.5:4b && ollama run --verbose qwen3.5:4b

    • ›Adds Qwen3.5 model series (0.8B, 2B, 4B, 9B parameters) to the Ollama library.
    • ›ollama run --verbose now shows peak memory usage when using Ollama's MLX engine.
59. v0.17.4 Feb 27, 2026 · issue -171

    Ollama v0.17.4 adds Qwen 3.5 and LFM 2 models plus tool call indices in parallel tool calls.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.17.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.17.4

    └──▷ TRY IT
    Pull and run the new Qwen 3.5 multimodal model for local inference.
    copy

    $ ollama run qwen3.5

    Pull and run LFM2 for efficient on-device deployment with a large-scale hybrid model.
    copy

    $ ollama run lfm2

    • ›Adds Qwen 3.5, a multimodal open-source model family, available via ollama pull qwen3.5.
    • ›Adds LFM 2, a hybrid on-device model family including LFM2-24B-A2B (24B params, efficient inference), available via ollama pull lfm2.
    • ›Includes tool call indices in parallel tool call responses, enabling callers to correlate multiple simultaneous tool invocations.
    └──▷ BREAKING ON UPGRADE

    • !Users on v0.17.1 will not receive this update automatically and must re-download Ollama manually.
60. v0.17.1 Feb 24, 2026 · issue -174

    Ollama v0.17.1 adds Nemotron architecture, web search for tool-capable models, and auto-update download controls.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.17.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.17.1

    • ›Adds support for the Nemotron model architecture in Ollama's engine.
    • ›Enables web search capabilities for models that support tools via the Ollama app.
    • ›Adds configuration option to disable automatic update downloading.
    • ›Improves LFM2 and LFM2.5 model support in Ollama's engine.
    • ›MLX engine now delivers improved memory usage.
    └──▷ BREAKING ON UPGRADE

    • !ollama create no longer defaults to affine quantization for unquantized models when using the MLX engine — existing workflows relying on that default will produce differently quantized output.
61. v0.17.0 Feb 21, 2026 · issue -177

    Ollama v0.17.0 adds ollama launch openclaw for one-command OpenClaw setup with web search and open model support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.17.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.17.0

    └──▷ TRY IT
    Spin up a fully configured OpenClaw instance in one step to start using open models like Kimi-K2.5 without manual setup.
    copy

    $ ollama launch openclaw

    • ›New ollama launch openclaw command installs and configures OpenClaw automatically, enabling use with open models like Kimi-K2.5, GLM-5, and Minimax-M2.5.
    • ›Adds web search capability in OpenClaw when using cloud models, allowing internet-augmented responses.
    • ›macOS and Windows apps now automatically select context length based on available VRAM.
62. v0.16.3 Feb 19, 2026 · issue -179

    Ollama v0.16.3 adds Cline CLI integration, always-on model picker, and Gemma 3/Llama/Qwen 3 MLX support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.16.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.16.3

    └──▷ TRY IT
    Quickly spin up Cline with a local model — useful when you want an AI coding assistant running entirely on-device.
    copy

    $ ollama launch cline

    • ›New ollama launch cline subcommand launches the Cline CLI integration directly.
    • ›ollama launch <integration> now always shows the model picker, making model selection explicit on every launch.
    • ›Adds Gemma 3, Llama, and Qwen 3 architectures to the MLX runner, enabling local Apple Silicon acceleration for those model families.
63. v0.16.2 Feb 14, 2026 · issue -184

    Ollama v0.16.2 adds web search for cloud models and a new setting to block cloud data egress.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.16.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.16.2

    └──▷ TRY IT
    Keep all inference on-device — block cloud model access entirely for air-gapped or sensitive environments.
    copy

    $ OLLAMA_NO_CLOUD=1 ollama serve

    Run a live web-augmented query through Claude without leaving the Ollama CLI.
    copy

    $ ollama launch claude:cloud

    • ›Adds web search support when running ollama launch claude with :cloud models.
    • ›New OLLAMA_NO_CLOUD=1 environment variable (and app setting) to disable cloud models and keep data on-device.
64. v0.16.1 Feb 12, 2026 · issue -186

    Ollama v0.16.1 lets image generation models respect OLLAMA_LOAD_TIMEOUT and improves install UX on macOS and Windows.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.16.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.16.1

    • ›Image generation models now honor the OLLAMA_LOAD_TIMEOUT environment variable, enabling timeout control for slow-loading diffusion models.
    • ›macOS curl install script no longer prompts for a password unless elevation is actually required.
    • ›Windows iem install script now displays progress during installation.
65. v0.16.0 Feb 12, 2026 · issue -186

    Ollama v0.16.0 adds a new ollama launch command, Ctrl+G editor integration, and two new frontier models.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.16.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.16.0

    └──▷ TRY IT
    Launch the Pi app with a local model without manual setup — useful for quickly spinning up a model-backed app.
    copy

    $ ollama launch pi

    Open your $EDITOR mid-conversation to compose or edit a long or complex prompt comfortably, then send it on save.
    copy

    $ ollama run llama3
    # At the >>> prompt, press Ctrl+G to open the prompt in your text editor

    • ›New ollama launch command lets users start apps (e.g., Pi) pre-connected to a local model.
    • ›Ctrl+G keybinding opens an external text editor for editing prompts during an interactive model session.
    • ›MLX runner now supports GLM-4.7-Flash.
    • ›Adds GLM-5 (744B total / 40B active MoE) and MiniMax-M2.5 to the model library.
66. v0.15.6 Feb 7, 2026 · issue -191

    ollama launch now auto-downloads missing models instead of erroring out

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.6 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.15.6

    • ›Enables ollama launch to automatically download missing models on demand rather than returning an error.
67. v0.15.5 Feb 3, 2026 · issue -195

    Ollama v0.15.5 adds sub-agent support, browser-based sign-in, VRAM-aware context limits, and two new models.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.5 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.15.5

    └──▷ TRY IT
    Pass extra flags to a launched tool — useful when resuming a paused coding session via Claude.
    copy

    $ ollama launch claude -- --resume

    • ›Adds argument passthrough to ollama launch, enabling flags like --resume to be forwarded to the launched tool.
    • ›Adds sub-agent support to ollama launch for planning, deep research, and similar multi-step agentic workflows.
    • ›ollama signin now opens a browser window to the connect page for easier authentication.
    • ›Adds GLM-4.7-Flash support on Ollama's experimental MLX engine.
    • ›Adds new model Qwen3-Coder-Next, optimized for agentic coding workflows and local development.
    +1 moreshow less

    • ›Adds new model GLM-OCR, a multimodal model for complex document understanding.
68. v0.15.4 Feb 1, 2026 · issue -197

    Ollama v0.15.4 adds automatic OpenClaw onboarding flow to ollama launch openclaw.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.15.4

    └──▷ TRY IT
    Run OpenClaw for the first time and be guided through its onboarding flow automatically.
    copy

    $ ollama launch openclaw

    • ›Triggers the standard OpenClaw onboarding flow when running ollama launch openclaw for the first time.
69. v0.15.3 Feb 1, 2026 · issue -197

    Ollama v0.15.3: ollama launch now respects OLLAMA_HOST and improves Ministral tool calling

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.15.3

    └──▷ TRY IT
    Launch a model against a non-default Ollama host (e.g., a remote server) without extra flags — useful in multi-host or CI environments.
    copy

    $ OLLAMA_HOST=https://my-ollama-server:11434 ollama launch openclaw

    • ›Enables ollama launch to use the OLLAMA_HOST environment variable when connecting, so custom host configurations are honored automatically.
    • ›Improves tool calling support for Ministral models.
    └──▷ BREAKING ON UPGRADE

    • !The ollama launch clawdbot subcommand is renamed to ollama launch openclaw; any scripts or workflows invoking ollama launch clawdbot will break.
70. v0.15.2 Jan 27, 2026 · issue -202

    Ollama v0.15.2 adds ollama launch clawdbot to spin up Clawdbot using local Ollama models.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.15.2

    └──▷ TRY IT
    Launch a Clawdbot instance backed by your local Ollama models without any external API dependency.
    copy

    $ ollama launch clawdbot

    • ›New ollama launch clawdbot command launches Clawdbot powered by locally running Ollama models.
71. v0.15.0 Jan 21, 2026 · issue -208

    Ollama v0.15.0 adds ollama launch to connect local models with Claude Code, Codex, OpenCode, and Droid instantly.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.15.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.15.0

    • ›New ollama launch command integrates Ollama models with Claude Code, Codex, OpenCode, and Droid without separate configuration.
    • ›Supports <kbd>Ctrl</kbd>+<kbd>J</kbd> and <kbd>Shift</kbd>+<kbd>Enter</kbd> for inserting newlines in ollama run interactive sessions.
72. v0.14.3 Jan 16, 2026 · issue -213

    Ollama v0.14.3 adds image-generation support via /api/generate and two new text-to-image models.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.14.3

    └──▷ TRY IT
    Generate an image from a text prompt using the /api/generate API — no separate image endpoint needed.
    copy

    $ curl http://localhost:11434/api/generate -d '{"model": "x/z-image-turbo", "prompt": "a photorealistic mountain landscape at golden hour"}'

    • ›Adds Z-Image Turbo, a 6B-parameter text-to-image model from Alibaba's Tongyi Lab for high-quality photorealistic image generation.
    • ›Adds Flux.2 Klein, Black Forest Labs' fastest image-generation model to date.
    • ›Adds GLM-4.7-Flash, a 30B-class model optimized for lightweight deployment balancing performance and efficiency.
    • ›Adds LFM2.5-1.2B-Thinking, a hybrid model family designed for on-device deployment.
    • ›Enables image generation via the existing /api/generate API endpoint.
73. v0.14.2 Jan 16, 2026 · issue -213

    Ollama v0.14.2 adds multiline CLI input, improved OpenResponses API conformance, and the TranslateGemma 55-language model.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.14.2

    • ›Supports multiline input in the Ollama CLI via Shift+Enter or Ctrl+J.
    • ›Improves /v1/responses API conformance to the OpenResponses specification.
    • ›Adds TranslateGemma, a new collection of open translation models built on Gemma 3 supporting 55 languages.
74. v0.14.1 Jan 14, 2026 · issue -215

    Ollama v0.14.1 adds experimental image generation model support on macOS and Linux (CUDA).

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.14.1

    └──▷ TRY IT
    Generate images interactively using the first available experimental image generation model.
    copy

    $ ollama run x/z-image-turbo

    • ›Supports experimental image generation models on macOS and Linux (CUDA), starting with Z-Image-Turbo.
75. v0.14.0 Jan 10, 2026 · issue -219

    Ollama v0.14.0 adds an agent loop with bash tool, Anthropic API compatibility, image generation, and Modelfile version pinning.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.14.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.14.0

    └──▷ TRY IT
    Run an agent loop with bash tool access — useful for tasks that require multi-step reasoning and shell execution.
    copy

    $ ollama run --experimental llama3.2

    Call Ollama from an Anthropic-compatible client or SDK by pointing it at the /v1/messages endpoint.
    copy

    $ curl http://localhost:11434/v1/messages \
      -H 'Content-Type: application/json' \
      -d '{"model": "llama3.2", "max_tokens": 256, "messages": [{"role": "user", "content": "Hello!"}]}'

    • ›New ollama run --experimental flag opens an agent loop CLI with a built-in bash tool for agentic workflows.
    • ›Adds Anthropic API compatibility via the /v1/messages endpoint, enabling Anthropic-compatible clients to target Ollama.
    • ›New REQUIRES Modelfile command lets model authors declare the minimum Ollama version required to run the model.
    • ›Adds experimental support for image generation models powered by MLX.
    • ›Adds Swift source code syntax highlighting in the Ollama app.
    +1 moreshow less

    • ›Linux install bundles now use zst compression for faster downloads.
76. v0.13.5 Dec 18, 2025 · issue -242

    Ollama v0.13.5 adds BERT model support, DeepSeek-V3.1 tool parsing, and the FunctionGemma function-calling model.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.5 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.13.5

    • ›Adds built-in renderer and tool parsing for DeepSeek-V3.1, enabling structured function-calling workflows with that model.
    • ›New functiongemma model available: a Gemma 3 270M variant fine-tuned explicitly for function calling.
77. v0.13.4 Dec 13, 2025 · issue -247

    Ollama v0.13.4 adds Nemotron 3 Nano and OLMo 3/3.1 models, with Flash Attention now on by default.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.13.4

    • ›Adds Nemotron 3 Nano, an efficient open model optimized for agentic workloads.
    • ›Adds OLMo 3 and OLMo 3.1, open language models pre-trained on the Dolma 3 dataset and post-trained on Dolci datasets.
    • ›Enables Flash Attention automatically by default for all models, improving inference performance.
78. v0.13.3 Dec 9, 2025 · issue -251

    Ollama v0.13.3 adds Devstral-Small-2, rnj-1, and nomic-embed-text-v2-moe models plus improved embedding truncation.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.13.3

    • ›Adds Devstral-Small-2 (24B), a code-focused model optimized for multi-file editing and software engineering agents.
    • ›Adds rnj-1, an 8B dense model from Essential AI optimized for code and STEM tasks.
    • ›Adds nomic-embed-text-v2-moe, a multilingual Mixture-of-Experts text embedding model for multilingual retrieval.
    • ›Improves truncation logic for the /api/embed and /v1/embeddings endpoints.
79. v0.13.2 Dec 4, 2025 · issue -256

    Ollama v0.13.2 enables flash attention by default for vision models and adds Qwen3-Next.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.13.2

    └──▷ TRY IT
    Run the new Qwen3-Next model for fast, parameter-efficient inference.
    copy

    $ ollama run qwen3-next

    • ›Adds Qwen3-Next model, the first in the Qwen3-Next series, optimized for parameter efficiency and inference speed.
    • ›Enables flash attention by default for vision models (mistral-3, gemma3, qwen3-vl, and others), improving memory utilization and performance when processing image inputs.
80. v0.13.1 Nov 27, 2025 · issue -263

    Ollama v0.13.1 adds two new Mistral models, tool calling and thinking support for cogito-v2.1, and switches nomic-embed-text to Ollama's native engine.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.13.1

    └──▷ TRY IT
    Run the new edge-optimized Ministral-3 model locally for lightweight inference tasks.
    copy

    $ ollama run ministral-3

    Use cogito-v2.1 with tool calling enabled for agentic workflows.
    copy

    $ ollama run cogito-v2.1

    • ›Adds Ministral-3, an edge-optimized model designed to run on a wide range of hardware.
    • ›Adds Mistral-Large-3, a multimodal mixture-of-experts model for production-grade and enterprise workloads.
    • ›Enables tool calling support for the cogito-v2.1 model.
    • ›Adds thinking and tool parsing for cogito-v2.1.
    • ›Switches nomic-embed-text to use Ollama's native engine by default.
81. v0.13.0 Nov 19, 2025 · issue -271

    Ollama v0.13.0 adds DeepSeek-OCR, Cogito-V2.1, a new bench tool, and DeepSeek-V3.1 architecture support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.13.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.13.0

    └──▷ TRY IT
    Extract and convert a scanned document to markdown using DeepSeek-OCR with layout grounding.
    copy

    $ ollama run deepseek-ocr "/path/to/image\n<|grounding|>Convert the document to markdown."

    Benchmark a local model's token throughput to baseline performance or compare after hardware changes.
    copy

    $ go run ./cmd/bench -model gpt-oss:20b

    • ›Adds DeepSeek-OCR model support for document OCR, layout-grounded extraction, figure parsing, and markdown conversion from images.
    • ›Adds Cogito-V2.1 instruction-tuned model, currently the top open-weight LLM from a US company.
    • ›New bench CLI tool for benchmarking local model performance (built from the Ollama repo with Go).
    • ›Supports DeepSeek-V3.1 architecture natively in Ollama's engine.
82. v0.12.11 Nov 12, 2025 · issue -278

    Ollama v0.12.11 adds log probability support to its API and opt-in Vulkan GPU acceleration.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.11 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.11

    └──▷ TRY IT
    Retrieve per-token log probabilities to evaluate model confidence on a generation — useful for perplexity scoring or classification pipelines.
    copy

    $ curl http://localhost:11434/api/generate -d '{"model": "gemma3", "prompt": "Why is the sky blue?", "logprobs": true}'

    Inspect the top 3 alternative tokens at each position to understand model uncertainty or build autocomplete candidates.
    copy

    $ curl http://localhost:11434/api/generate -d '{"model": "gemma3", "prompt": "Why is the sky blue?", "logprobs": true, "top_logprobs": 3}'

    Enable Vulkan acceleration to run models on AMD, Intel, or integrated GPUs not supported by the default CUDA/Metal backends.
    copy

    $ OLLAMA_VULKAN=1 ollama serve

    • ›Adds logprobs field to Ollama's generate API and OpenAI-compatible API, returning per-token log probabilities and raw bytes for classification, evaluation, and perplexity tasks.
    • ›Adds top_logprobs parameter to expose the N most-likely alternative tokens at each position, enabling token-level introspection.
    • ›Adds opt-in Vulkan GPU acceleration via OLLAMA_VULKAN=1, broadening hardware support to AMD, Intel, and integrated GPUs.
    • ›Adds WebP image support in Ollama's desktop app.
    • ›Ollama now prefers dedicated GPUs over iGPUs when scheduling models.
83. v0.12.10 Nov 5, 2025 · issue -285

    Ollama v0.12.10 adds embedding model support in ollama run, tool call IDs in the chat API, and Vulkan GPU improvements.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.10 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.10

    └──▷ TRY IT
    Generate a vector embedding from a string using an embedding model directly in the CLI.
    copy

    $ ollama run embeddinggemma "Hello world"

    Pipe text into an embedding model from a file or another command for batch or scripted embedding workflows.
    copy

    $ echo "Hello world" | ollama run embeddinggemma

    • ›Enables ollama run to generate vector embeddings by running embedding models directly from the CLI, including via stdin piping.
    • ›Returns tool call IDs from the /api/chat API endpoint.
    • ›Enables flash attention for Vulkan GPU backends.
    • ›Adds Vulkan memory detection for Intel GPUs using DXGI+PDH.
    • ›Shows login instructions when switching to a cloud model in interactive mode.
84. v0.12.8 Oct 30, 2025 · issue -291

    Ollama v0.12.8 adds flash attention for qwen3-vl and automatic model unload before removal.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.8 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.8

    • ›Enables flash attention by default for qwen3-vl, improving inference performance.
85. v0.12.7 Oct 29, 2025 · issue -292

    Ollama v0.12.7 adds Qwen3-VL and MiniMax-M2 models, file uploads in the app, adjustable thinking levels, and OpenAI-compatible embedding format support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.7 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.7

    └──▷ TRY IT
    Request base64-encoded embeddings via the OpenAI-compatible endpoint — useful when piping embeddings into downstream systems that expect a specific format.
    copy

    $ curl http://localhost:11434/v1/embeddings -H 'Content-Type: application/json' -d '{"model": "nomic-embed-text", "input": "Detect lateral movement in auth logs", "encoding_format": "base64"}'

    • ›Adds Qwen3-VL multimodal model support in sizes from 2B to 235B parameters.
    • ›Adds MiniMax-M2, a 230B parameter model optimized for coding and agentic workflows, available on Ollama's cloud.
    • ›New app UI: attach one or multiple files when prompting a model.
    • ›New app UI: adjust thinking levels for gpt-oss models to tune response depth.
    • ›The OpenAI-compatible /v1/embeddings endpoint now supports the encoding_format parameter.
    +2 moreshow less

    • ›Extends tool-call parsing to handle responses that don't conform to the standard {"name": name, "arguments": args} format.
    • ›New API documentation site launched at https://docs.ollama.com/api.
86. v0.12.6 Oct 15, 2025 · issue -306

    Ollama v0.12.6 adds tool-call search support, default flash attention for Gemma 3, and experimental Vulkan GPU backend.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.6 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.6

    • ›Adds web/tool-call search capability when running DeepSeek-V3.1, Qwen3, and other tool-calling-compatible models.
    • ›Enables flash attention by default for Gemma 3, improving performance and memory utilization.
    • ›Introduces experimental Vulkan GPU backend (build-from-source only), extending support to AMD and Intel GPUs not currently supported by Ollama.
87. v0.12.5 Oct 10, 2025 · issue -311

    Ollama v0.12.5 adds structured output support for thinking models via /api/chat

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.5 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.5

    └──▷ TRY IT
    Use structured output with a thinking model (e.g. deepseek-r1) to get schema-constrained JSON responses from the /api/chat endpoint
    copy

    $ curl http://localhost:11434/api/chat -d '{"model": "deepseek-r1", "messages": [{"role": "user", "content": "Extract the name and age from: John is 30 years old."}], "format": {"type": "object", "properties": {"name": {"type": "string"}, "age": {"type": "integer"}}, "required": ["name", "age"]}, "stream": false}'

    • ›Supports structured outputs for thinking models when using the /api/chat API
    └──▷ BREAKING ON UPGRADE

    • !macOS 12 Monterey and macOS 13 Ventura are no longer supported.
    • !AMD gfx900 and gfx906 (MI50, MI60, etc) GPUs are no longer supported via ROCm.
88. v0.12.4 Oct 3, 2025 · issue -317

    Ollama v0.12.4 enables flash attention by default for Qwen3 models and adds a new override to disable it.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.4

    └──▷ TRY IT
    Disable flash attention for a Qwen3 model if you encounter compatibility issues, overriding the new default.
    copy

    $ OLLAMA_FLASH_ATTENTION=0 ollama run qwen3

    • ›Enables flash attention by default for Qwen3 and Qwen3 Coder models, improving inference performance without manual configuration.
    • ›Adds support for overriding default flash attention via OLLAMA_FLASH_ATTENTION=0 for models where it is enabled by default.
    └──▷ BREAKING ON UPGRADE

    • !macOS 12 Monterey and macOS 13 Ventura are no longer supported.
    • !AMD gfx900 and gfx906 (MI50, MI60, etc.) GPUs are no longer supported via ROCm.
89. v0.12.3 Sep 26, 2025 · issue -324

    Ollama v0.12.3 adds DeepSeek-V3.1 and Kimi-K2 models plus sign-in URL prompting on push.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.3 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.3

    └──▷ TRY IT
    Run DeepSeek-V3.1-Terminus on Ollama's cloud when you need a hybrid thinking/non-thinking model without local VRAM requirements.
    copy

    $ ollama run deepseek-v3.1:671b-cloud

    Run Kimi-K2's trillion-parameter MoE model via the cloud for state-of-the-art reasoning tasks.
    copy

    $ ollama run kimi-k2:1t-cloud

    • ›Adds DeepSeek-V3.1-Terminus, a hybrid model supporting both thinking and non-thinking modes, runnable locally or on Ollama's cloud.
    • ›Adds Kimi-K2-Instruct-0905, a 1-trillion-parameter MoE model with 32B activated parameters, available via cloud.
    • ›ollama push now outputs a sign-in URL when authentication is required.
90. v0.12.2 Sep 24, 2025 · issue -326

    Ollama v0.12.2 adds a web search API to ground model responses in live data and expands new-engine model support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.2 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.2

    • ›New web search API lets models retrieve live web results to reduce hallucinations and improve accuracy, with a free tier for individuals and higher rate limits via Ollama Cloud.
    • ›Qwen3 architecture models, including MoE variants, now run on Ollama's new engine.
    • ›Supports multi-regex pretokenizers in Ollama's new engine.
    • ›Ollama's new engine can load tensors by matching a prefix or suffix.
91. v0.12.1 Sep 21, 2025 · issue -329

    Ollama v0.12.1 adds Qwen3 Embedding model support and tool calling for Qwen3-Coder.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.1 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.1

    └──▷ TRY IT
    Generate embeddings locally with the new state-of-the-art Qwen3 Embedding model for use in RAG pipelines or semantic search.
    copy

    $ ollama pull qwen3-embedding

    • ›Adds Qwen3 Embedding, a state-of-the-art open embedding model from the Qwen team, available via ollama pull qwen3-embedding.
    • ›Enables tool calling support for Qwen3-Coder models.
92. v0.12.0 Sep 18, 2025 · issue -332

    Ollama v0.12.0 adds cloud-hosted large models, native BERT and Qwen3 engine support, and smarter thinking-prompt handling.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.12.0 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.12.0

    └──▷ TRY IT
    Run a cloud-hosted large model when local hardware is insufficient for multi-hundred-billion-parameter inference.
    copy

    $ ollama run qwen3-coder:480b-cloud

    • ›Adds cloud model support (preview): run massive models like qwen3-coder:480b on datacenter-grade hardware with the -cloud tag suffix.
    • ›Supports BERT-architecture models natively on Ollama's own engine.
    • ›Supports Qwen3-architecture models natively on Ollama's own engine.
    • ›Skips parsing an initial <think> block when it is provided in the prompt for /api/generate, enabling cleaner reasoning-model workflows.
93. v0.11.11 Sep 11, 2025 · issue -339

    Ollama v0.11.11 adds CUDA 13 support and a new dimensions field for embed requests.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.11 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.11.11

    └──▷ TRY IT
    Request embeddings at a specific dimensionality — useful when downstream vector stores require a fixed embedding size.
    copy

    $ curl http://localhost:11434/api/embed -d '{"model": "nomic-embed-text", "input": "Why is the sky blue?", "dimensions": 512}'

    • ›Supports CUDA 13 for GPU-accelerated inference.
    • ›Adds dimensions field to embed requests, enabling control over output embedding size.
    • ›Enables new memory estimates in Ollama's new engine by default, improving resource planning for hybrid and recurrent models.
    • ›Adds Cmd+/- zoom controls for text sizing in Ollama's desktop app.
    • ›Enables copying of assistant messages in Ollama's desktop app.
94. v0.11.10 Sep 4, 2025 · issue -346

    Ollama v0.11.10 adds support for EmbeddingGemma, a new best-in-class open embedding model.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.10 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.11.10

    • ›Supports EmbeddingGemma, a new open embedding model with best-in-class performance for its size.
95. v0.11.9 Sep 2, 2025 · issue -348

    Ollama v0.11.9 overlaps GPU and CPU computations for improved inference performance.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.9 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.11.9

    • ›Improves performance by overlapping GPU and CPU computations during inference.
96. v0.11.8 Aug 27, 2025 · issue -354

    Ollama v0.11.8 enables flash attention by default for gpt-oss on supported hardware.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.8 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.11.8

    • ›Enables flash attention by default for gpt-oss models on systems that support it, reducing memory overhead during inference.
97. v0.11.7 Aug 25, 2025 · issue -356

    Ollama v0.11.7 adds DeepSeek-V3.1 support with hybrid thinking and cloud Turbo mode preview.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.7 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.11.7

    └──▷ TRY IT
    Run DeepSeek-V3.1 with thinking enabled to get chain-of-thought reasoning alongside the final answer.
    copy

    $ curl http://localhost:11434/api/chat -d '{"model": "deepseek-v3.1", "messages": [{"role": "user", "content": "why is the sky blue?"}], "think": true}'

    Run DeepSeek-V3.1 on Ollama's cloud hardware when local VRAM is insufficient for the 671B model.
    copy

    $ OLLAMA_HOST=ollama.com ollama run deepseek-v3.1

    Toggle thinking on or off interactively during a CLI chat session with a hybrid-thinking model.
    copy

    $ /set think
    # or to disable:
    /set nothink

    • ›Adds DeepSeek-V3.1 (671B parameter model) to the Ollama model library.
    • ›Supports hybrid thinking on compatible models: enable or disable chain-of-thought reasoning per request via the think field in the API or /set think//set nothink CLI commands.
    • ›Introduces Turbo mode (preview): routes inference for large models like DeepSeek-V3.1 to cloud hardware via OLLAMA_HOST=ollama.com.
98. v0.11.5 Aug 15, 2025 · issue -363

    Ollama v0.11.5 adds opt-in improved VRAM memory estimates, multi-GPU scheduling gains, and CPU flash attention support.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.5 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.11.5

    └──▷ TRY IT
    Try the new VRAM estimator before it becomes the default — useful if you're hitting out-of-memory errors with large models on a multi-GPU machine.
    copy

    $ OLLAMA_NEW_ESTIMATES=1 ollama serve

    Speed up inference on CPU-only hosts (e.g., a server with no GPU) by enabling flash attention, which was previously a GPU-only optimization.
    copy

    $ OLLAMA_FLASH_ATTENTION=1 ollama serve

    • ›New opt-in memory management (OLLAMA_NEW_ESTIMATES=1) improves VRAM utilization and reduces out-of-memory errors when scheduling models on GPUs.
    • ›Improved multi-GPU scheduling reduces VRAM allocation when running across more than 2 GPUs.
    • ›Enables flash attention for pure-CPU models via OLLAMA_FLASH_ATTENTION=1.
    • ›The Ollama app now persists default model, Turbo, and Web Search selections across restarts.
99. v0.11.4 Aug 7, 2025 · issue -363

    Ollama v0.11.4 improves OpenAI-compatible API support: simultaneous content+tool calls, tool name propagation, and always-on reasoning.

    └──▷ GET THIS VERSION
    copy

    $ git clone --branch v0.11.4 https://github.com/ollama/ollama.git
    # already have the repo? check out this version:
    $ git checkout v0.11.4

    • ›Supports content and tool calls coexisting in the same OpenAI-compatible message, enabling richer agentic responses.
    • ›Propagates the tool name when converting role=tool messages in the OpenAI-compatible layer.
    • ›Always provides reasoning output in OpenAI-compatible responses.
100. v0.11.0 Aug 5, 2025 · issue -363

     Ollama v0.11 adds native support for OpenAI's gpt-oss 20B and 120B open-weight models with built-in web search and MXFP4 quantization.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.11.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.11.0

     └──▷ TRY IT
     Run the smaller gpt-oss model locally on a 16 GB system for reasoning or agentic tasks.
     copy

     $ ollama run gpt-oss:20b

     Run the larger gpt-oss model on an 80 GB GPU for high-capacity reasoning workloads.
     copy

     $ ollama run gpt-oss:120b

     • ›Adds OpenAI gpt-oss 20B and 120B open-weight models, runnable locally via ollama run gpt-oss:20b and ollama run gpt-oss:120b.
     • ›Supports native MXFP4 quantization format for gpt-oss MoE weights (4.25 bits/param), enabling the 20B to run on 16 GB RAM and the 120B on a single 80 GB GPU.
     • ›Enables built-in optional web search to augment gpt-oss models with real-time information.
     • ›Supports configurable reasoning effort (low, medium, high) for gpt-oss models to balance quality and latency.
     • ›Exposes full chain-of-thought reasoning output from gpt-oss models.
     +2 moreshow less

     • ›Supports function calling, Python tool calls, and structured outputs via gpt-oss models' native agentic capabilities.
     • ›Adds SWA (sliding window attention) KV-cache enhancement to retain additional cache entries.
101. v0.10.0 Jul 18, 2025 · issue -364

     Ollama v0.10.0 adds context-length visibility in ollama ps, WebP image support, and 10-30% multi-GPU performance gains.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.10.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0

     └──▷ TRY IT
     Inspect context window size of every currently loaded model to verify memory headroom before routing long-context requests.
     copy

     $ ollama ps

     • ›Adds context length display to ollama ps output for loaded models.
     • ›Supports WebP images in the OpenAI-compatible API.
     • ›Delivers 10-30% performance improvement when using multiple GPUs.
     • ›Improves performance of gemma3n models by 2-3x.
     • ›Launches redesigned desktop app for macOS and Windows.
     └──▷ BREAKING ON UPGRADE

     • !Parallel request processing now defaults to 1 (previously higher), which will reduce throughput for workloads relying on the previous concurrent-request default.
102. v0.9.6 Jul 8, 2025 · issue -364

     Ollama v0.9.6 lets tool-role messages carry a tool_name field in /api/chat.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.6 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.9.6

     └──▷ TRY IT
     Attribute a tool result to a specific tool by name when replying to a model's tool call in a multi-turn chat session.
     copy

     $ curl http://localhost:11434/api/chat -d '{"model": "llama3", "messages": [{"role": "user", "content": "What is the weather in Paris?"}, {"role": "assistant", "tool_calls": [{"function": {"name": "get_weather", "arguments": {"city": "Paris"}}}]}, {"role": "tool", "tool_name": "get_weather", "content": "Sunny, 22°C"}]}'

     • ›Supports tool_name field in messages with "role": "tool" via the /api/chat endpoint, enabling precise tool-call attribution in multi-turn agentic conversations.
103. v0.9.5 Jul 2, 2025 · issue -364

     Ollama v0.9.5 adds network exposure, configurable model directory, and a faster native macOS app.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.5 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.9.5

     • ›Enables exposing Ollama over the network so other devices (including low-powered ones) can access a centrally running instance.
     • ›Supports configuring the model storage directory, enabling models to live on external drives or custom paths.
     • ›Ships a native macOS application with smaller installation footprint and faster startup time.
     • ›Adds NativeMind to the Community Integrations list.
     └──▷ BREAKING ON UPGRADE

     • !Ollama for macOS now requires version 12 (Monterey) or newer; installations on older macOS versions will no longer be supported.
104. v0.9.4 Jun 27, 2025 · issue -365

     Ollama v0.9.4 adds network exposure and configurable model directory via the desktop apps.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.4 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.9.4

     • ›Enables exposing the Ollama server on the network so other devices (or remote users) can access models running on a powerful local machine.
     • ›Adds configurable model storage directory, allowing models to be stored on external drives or any non-default path.
     • ›Delivers a native macOS app with significantly smaller install footprint and faster startup.
     └──▷ BREAKING ON UPGRADE

     • !Ollama for macOS now requires version 12 (Monterey) or newer; installations on older macOS versions will no longer be supported.
105. v0.9.3 Jun 25, 2025 · issue -365

     Ollama v0.9.3 adds support for Google's Gemma 3n models, optimized for laptops, tablets, and phones.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.3 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.9.3

     └──▷ TRY IT
     Run the Effective 2B Gemma 3n model locally for lightweight, multilingual inference on everyday hardware.
     copy

     $ ollama run gemma3n:e2b

     Run the Effective 4B Gemma 3n model for higher-quality multilingual responses while remaining efficient on consumer devices.
     copy

     $ ollama run gemma3n:e4b

     • ›Supports Gemma 3n models (e2b and e4b variants), designed for efficient on-device execution across laptops, tablets, and phones with training data covering 140+ spoken languages.
106. v0.9.1 Jun 9, 2025 · issue -365

     Ollama v0.9.1 adds tool calling for DeepSeek-R1 671B and Magistral, plus a redesigned macOS/Windows preview app.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.1 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.9.1

     └──▷ TRY IT
     Pull DeepSeek-R1-2508 (671B) or Magistral to start using the newly supported tool calling capability.
     copy

     $ ollama pull deepseek-r1:671b

     • ›Adds tool calling support for DeepSeek-R1-2508 (671B) and Magistral models.
     • ›Supports disabling thinking mode on Magistral (with recommended system prompt change).
     • ›New preview macOS and Windows desktop apps with network exposure, local browser access, and configurable model directory.
     • ›macOS app rebuilt as a native application for smaller footprint and faster startup.
     • ›Enables exposing Ollama on the network so other devices (or remote users) can reach a central Ollama host.
     +2 moreshow less

     • ›Allows local browser access so web applications can directly call the local Ollama API.
     • ›Model storage directory is now configurable, enabling use of external drives or custom paths.
107. v0.9.0 May 29, 2025 · issue -366

     Ollama v0.9.0 adds controllable thinking mode for reasoning models, exposing chain-of-thought as a separate API field.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.9.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.9.0

     └──▷ TRY IT
     Toggle thinking off mid-session in the CLI when you want faster responses without reasoning output.
     copy

     $ ollama run deepseek-r1
     >>> /set nothink

     • ›Adds thinking mode support: enable or disable chain-of-thought reasoning for compatible models (DeepSeek R1, Qwen 3) independently per request.
     • ›New thinking field in API chat responses separates the model's reasoning trace from its final content for easy parsing.
     • ›New /set think and /set nothink CLI commands toggle thinking mode interactively during a session.
     • ›New "think": true/false API parameter in /api/chat allows per-request control of thinking behavior.
     • ›Adds support for DeepSeek-R1-0528, the updated 8B distilled and 671B full models with improved reasoning.
108. v0.8.0 May 27, 2025 · issue -366

     Ollama v0.8.0 adds streaming support for tool call responses.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.8.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.8.0

     • ›Streams responses that include tool calls, enabling real-time output during tool-augmented LLM interactions.
     • ›Adds improved memory estimate debug information in logs when running models in Ollama's engine.
109. v0.7.1 May 21, 2025 · issue -366

     Ollama v0.7.1 adds Qwen 3 & Qwen 2 multimodal support and truncation indicators in ollama show.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.1 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.7.1

     • ›Supports Alibaba's Qwen 3 and Qwen 2 architectures in Ollama's multimodal engine.
     • ›ollama show now displays ... when output data is truncated.
110. v0.7.0 May 13, 2025 · issue -366

     Ollama v0.7.0 adds multimodal vision model support, WebP image input, and corrected HTTP 405 responses.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.7.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.7.0

     • ›Supports multimodal vision models via Ollama's new engine, including Meta Llama 4, Google Gemma 3, Qwen 2.5 VL, and Mistral Small 3.1.
     • ›Accepts WebP images as input to multimodal models.
     • ›API now returns HTTP 405 (Method Not Allowed) instead of 404 for disallowed methods, enabling more accurate client-side error handling.
     • ›Improved performance of importing safetensors models via ollama create.
     • ›Improved prompt processing speeds of Qwen3 MoE on macOS.
111. v0.6.8 May 3, 2025 · issue -366

     Ollama v0.6.8 delivers major performance gains for Qwen3 MoE models on NVIDIA and AMD GPUs.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.8 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.8

     • ›Improves inference performance for Qwen3 MoE models (30b-a3b and 235b-a22b) on NVIDIA and AMD GPUs.
112. v0.6.7 Apr 26, 2025 · issue -367

     Ollama v0.6.7 adds Llama 4 multimodal, Qwen3, Phi 4 reasoning models, and raises default context window to 4096 tokens.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.7 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.7

     └──▷ TRY IT
     Pull and run Phi 4 Reasoning for complex, multi-step reasoning tasks without extra configuration.
     copy

     $ ollama run phi4-reasoning

     Pull Qwen3 MoE variant to leverage mixture-of-experts efficiency for large-context inference.
     copy

     $ ollama run qwen3

     • ›Adds support for Meta's Llama 4 multimodal models, enabling image-and-text inference locally.
     • ›Adds support for Microsoft's Phi 4 Reasoning and Phi 4 Mini Reasoning models for state-of-the-art chain-of-thought tasks.
     • ›Adds Qwen3 family (dense and MoE variants) to the model library.
     • ›Increases default context window from its previous limit to 4096 tokens, unlocking longer conversations and documents out of the box.
113. v0.6.6 Apr 17, 2025 · issue -367

     Ollama v0.6.6 adds IBM Granite 3.3 and DeepCoder models, experimental faster downloader, and expanded tool-call type support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.6 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.6

     └──▷ TRY IT
     Enable the experimental faster downloader to get improved pull speeds and reliability before it becomes default.
     copy

     $ OLLAMA_EXPERIMENT=client2 ollama serve

     • ›Adds IBM Granite 3.3 (2B and 8B) models with 128K context length, fine-tuned for reasoning and instruction-following.
     • ›Adds DeepCoder 14B (and 1.5B) fully open-source coder model at O3-mini level.
     • ›New experimental faster model downloader with improved performance and reliability, enabled via OLLAMA_EXPERIMENT=client2.
     • ›Improves performance of ollama create when importing models from Safetensors.
     • ›Supports tool function parameters with either a single type or an array of types.
     +2 moreshow less

     • ›Includes items and $defs fields in the API to properly handle array types.
     • ›Adds OpenAI-Beta headers to the CORS safelist, enabling broader cross-origin API access.
114. v0.6.5 Apr 6, 2025 · issue -367

     Ollama v0.6.5 adds Mistral Small 3.1, a top-performing vision model in its weight class.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.5 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.5

     └──▷ TRY IT
     Pull and run Mistral Small 3.1 to get vision-capable inference locally.
     copy

     $ ollama run mistral-small3.1

     • ›Adds support for Mistral Small 3.1, described as the best-performing vision model in its weight class.
115. v0.6.4 Apr 2, 2025 · issue -367

     Ollama v0.6.4 adds model capability metadata to /api/show and AMD RDNA4 GPU support on Linux.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.4 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.4

     └──▷ TRY IT
     Programmatically detect whether a locally pulled model supports vision before routing multimodal requests to it.
     copy

     $ curl http://localhost:11434/api/show -d '{"name": "llava"}'

     • ›Adds model capability metadata (e.g. vision) to /api/show API responses.
     • ›Adds AMD RDNA4 GPU support on Linux.
116. v0.6.3 Mar 22, 2025 · issue -368

     Ollama v0.6.3 adds sliding window attention optimizations for Gemma 3 and smarter ollama create for safetensors imports.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.3 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.3

     • ›Adds sliding window attention optimizations for Gemma 3, improving inference speed and memory efficiency for long context windows.
     • ›ollama create now reports the name of unsupported architectures instead of failing silently.
117. v0.6.2 Mar 18, 2025 · issue -368

     Ollama v0.6.2 adds multi-image support for Gemma 3 and AMD Strix Halo GPU support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.2 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.2

     • ›Supports multiple images in a single Gemma 3 prompt, enabling multimodal workflows.
     • ›Adds support for AMD Strix Halo GPUs.
     • ›ollama create --quantize now works when converting Gemma 3 models from safetensors format.
118. v0.6.1 Mar 14, 2025 · issue -368

     Ollama v0.6.1 adds Command A model support, verbose model inspection, and new CLI hotkeys.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.1 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.1

     └──▷ TRY IT
     Inspect full model metadata and configuration details — useful when debugging model behavior or confirming quantization and parameters.
     copy

     $ ollama show --verbose llama3

     Pull and run the new Command A enterprise model for high-quality reasoning tasks.
     copy

     $ ollama run command-a

     • ›Adds Command A, a 111B-parameter enterprise-grade model, to the Ollama library.
     • ›New ollama show --verbose / ollama show -v flag prints additional model data beyond the default output.
     • ›Adds Ctrl+P and Ctrl+N hotkeys for navigating history in ollama run interactive sessions.
119. v0.6.0 Mar 11, 2025 · issue -368

     Ollama v0.6.0 adds support for Google Gemma 3 in 1B, 4B, 12B, and 27B parameter sizes.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.6.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.6.0

     └──▷ TRY IT
     Run the Gemma 3 27B model locally for a large-context reasoning task.
     copy

     $ ollama run gemma3:27b

     • ›Supports Google Gemma 3 multimodal model in 1B, 4B, 12B, and 27B parameter sizes via ollama run gemma3.
120. v0.5.13 Feb 27, 2025 · issue -369

     Ollama v0.5.13 adds NVIDIA Blackwell support, a new default context length env var, and three new models including Phi-4-Mini with function calling.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.13 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.13

     └──▷ TRY IT
     Set a server-wide default context length of 8K so all models use it without per-request configuration.
     copy

     $ OLLAMA_CONTEXT_LENGTH=8192 ollama serve

     • ›New OLLAMA_CONTEXT_LENGTH environment variable lets operators set the default context length server-wide without per-request overrides.
     • ›Ollama is now compiled for NVIDIA Blackwell GPUs, enabling inference on the latest NVIDIA hardware.
     • ›Adds Phi-4-Mini model with multilingual support, reasoning, mathematics, and function calling.
     • ›Adds Granite-3.2-Vision, a compact vision-language model for visual document understanding (tables, charts, diagrams, infographics).
     • ›Adds Command R7B Arabic, a model optimized for advanced Arabic language tasks targeting MENA enterprises.
     +1 moreshow less

     • ›Accepts requests from Visual Studio Code and Cursor via origins beginning with vscode-file://, enabling IDE-native integration.
     └──▷ BREAKING ON UPGRADE

     • !Ubuntu 20.04, Debian 10, and RHEL 8+ or later are now required to run Ollama on Linux — older Linux distributions are no longer supported.
121. v0.5.12 Feb 20, 2025 · issue -369

     Ollama v0.5.12 adds Perplexity R1 1776, OpenAI-compatible tool_calls responses, and X-Stainless-Timeout header support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.12 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.12

     └──▷ TRY IT
     Pull and run the new Perplexity R1 1776 model for sensitive-topic research queries it previously refused.
     copy

     $ ollama run r1-1776

     • ›Adds Perplexity R1 1776 model: a post-trained DeepSeek-R1 variant with fewer topic refusals.
     • ›OpenAI-compatible API now returns tool_calls in responses when a model invokes a tool.
     • ›Accepts X-Stainless-Timeout as a valid header on OpenAI API endpoints.
122. v0.5.9 Feb 12, 2025 · issue -369

     Ollama v0.5.9 adds DeepScaleR and OpenThinker reasoning models to the library.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.9 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.9

     └──▷ TRY IT
     Run the compact DeepScaleR math-reasoning model locally for step-by-step problem solving without needing a large GPU.
     copy

     $ ollama run deepscaler

     Pull and run OpenThinker for open-source chain-of-thought reasoning tasks.
     copy

     $ ollama run openthinker

     • ›Adds DeepScaleR, a 1.5B-parameter math-reasoning model fine-tuned on Deepseek-R1-Distilled-Qwen-1.5B, available via ollama pull deepscaler.
     • ›Adds OpenThinker, a fully open-source family of reasoning models distilled from DeepSeek-R1, available via ollama pull openthinker.
123. v0.5.8 Feb 5, 2025 · issue -369

     Ollama v0.5.8 adds AVX-512 CPU acceleration and broadens GPU compatibility to non-AVX hosts

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.8 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.8

     • ›Adds AVX-512 instruction support for additional CPU inference acceleration on compatible hardware.
     • ›Enables NVIDIA and AMD GPUs on systems whose CPUs lack AVX instructions, broadening deployment targets.
     • ›Adds AVX2 instruction usage when offloading to NVIDIA and AMD GPUs for improved hybrid performance.
     • ›New ollama-darwin.tgz archive package replaces the previous ollama-darwin standalone binary for macOS distribution.
     └──▷ BREAKING ON UPGRADE

     • !The ollama-darwin standalone binary is replaced by the ollama-darwin.tgz package; scripts or pipelines that download the old binary path will break.
     • !The steps to build Ollama with GPU acceleration from source have changed; existing build procedures must be updated per the development documentation.
124. v0.5.7 Jan 16, 2025 · issue -370

     Ollama v0.5.7 adds native import support for Command R and Command R+ safetensor models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.7 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.7

     • ›Supports importing Command R and Command R+ architectures directly from safetensors files.
125. v0.5.5 Jan 8, 2025 · issue -370

     Ollama v0.5.5 adds 8 new models including DeepSeek-V3 and Phi-4, plus a faster /api/create endpoint that now accepts JSON.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.5 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.5

     • ›Adds Phi-4 (14B, Microsoft) to the model library.
     • ›Adds Command R7B (Cohere) for efficient inference on commodity GPUs and edge devices.
     • ›Adds DeepSeek-V3, a 671B MoE model with 37B parameters activated per token.
     • ›Adds OLMo 2 (7B and 13B) trained on up to 5T tokens.
     • ›Adds Dolphin 3, a general-purpose instruct-tuned model supporting coding, math, agentic, and function-calling use cases.
     +4 moreshow less

     • ›Adds SmallThinker, a small reasoning model fine-tuned from Qwen 2.5 3B Instruct.
     • ›Adds Granite 3.1 Dense (2B and 8B) from IBM, trained on over 12 trillion tokens.
     • ›Adds Granite 3.1 MoE (1B and 3B) from IBM, designed for low-latency long-context inference.
     • ›Updates the /api/create endpoint to improve model conversion speed and accept a JSON object body.
     └──▷ BREAKING ON UPGRADE

     • !The /api/create API endpoint (used by ollama create) is not backwards compatible: both the Ollama server and the ollama CLI must be version 0.5.5 or later, and the Python/JavaScript ollama library must be updated to the latest version when calling ollama.create.
126. v0.5.4 Dec 17, 2024 · issue -371

     Ollama v0.5.4 adds the Falcon3 family of sub-10B models optimised for science, math, and coding.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.4 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.4

     └──▷ TRY IT
     Pull and run a Falcon3 model locally for coding or math tasks.
     copy

     $ ollama run falcon3

     • ›Adds Falcon3 model family (sub-10B parameters) with strong performance in science, math, and coding tasks.
127. v0.5.2 Dec 11, 2024 · issue -371

     Ollama v0.5.2 adds EXAONE 3.5 bilingual models (2.4B–32B) and case-insensitive OLLAMA_ORIGINS host matching.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.2 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.2

     • ›Adds EXAONE 3.5 instruction-tuned bilingual (English/Korean) models ranging from 2.4B to 32B parameters, developed by LG AI Research.
     • ›OLLAMA_ORIGINS now matches hosts case-insensitively, simplifying origin allowlist configuration.
     └──▷ BREAKING ON UPGRADE

     • !The Linux ollama-linux-amd64.tgz directory structure has changed — manual Linux installations must retain the new directory layout and contents of the tar file after upgrading.
128. v0.5.0 Dec 4, 2024 · issue -371

     Ollama v0.5.0 adds JSON-schema structured outputs and experimental KV cache quantization to cut VRAM usage.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.5.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.5.0

     └──▷ TRY IT
     Enforce a strict JSON schema on model output so downstream code can parse it reliably without extra validation.
     copy

     $ curl -X POST http://localhost:11434/api/chat -H "Content-Type: application/json" -d '{"model": "llama3.1", "messages": [{"role": "user", "content": "Tell me about Canada."}], "stream": false, "format": {"type": "object", "properties": {"name": {"type": "string"}, "capital": {"type": "string"}, "languages": {"type": "array", "items": {"type": "string"}}}, "required": ["name", "capital", "languages"]}}'

     Run Ollama with 4-bit KV cache quantization to fit longer context windows into limited GPU VRAM.
     copy

     $ OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q4_0 ollama serve

     • ›Supports structured outputs via JSON schema in the format parameter across the REST API, Python library, and JavaScript library — constraining model responses to a defined shape.
     • ›Adds Llama 3.3 (70B) model, offering performance comparable to Llama 3.1 405B.
     • ›Adds Snowflake Arctic Embed 2, a multilingual frontier embedding model.
     • ›Experimental OLLAMA_KV_CACHE_TYPE env var enables KV cache quantization at 4-bit (q4_0), 8-bit (q8_0), or 16-bit (f16), reducing VRAM requirements for longer context windows.
129. v0.4.6 Nov 28, 2024 · issue -372

     Ollama v0.4.6 adds QwQ reasoning model, streaming tool calls, and SVG input validation.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.6 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.4.6

     └──▷ TRY IT
     Run the new QwQ reasoning model interactively to leverage its advanced chain-of-thought capabilities.
     copy

     $ ollama run qwq

     • ›Adds QwQ, an experimental AI reasoning model from the Qwen team, available via ollama pull qwq.
     • ›Tool calls are now included in streaming responses, enabling real-time agentic workflows without waiting for full completion.
     • ›Ollama now returns an explicit error when an SVG image is submitted, surfacing unsupported input early.
130. v0.4.5 Nov 26, 2024 · issue -372

     Ollama v0.4.5 lets ollama push print the uploaded model URL and accepts X-Stainless-Retry-Count from OpenAI clients.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.5 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.4.5

     • ›Accepts X-Stainless-Retry-Count header used by many OpenAI API clients, improving compatibility.
     • ›ollama push now prints the uploaded model URL on ollama.com after a successful push.
131. v0.4.4 Nov 23, 2024 · issue -372

     Ollama v0.4.4 adds Marco-o1 reasoning model and clean file-redirect output.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.4 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.4.4

     └──▷ TRY IT
     Run the new Marco-o1 reasoning model for complex problem-solving tasks.
     copy

     $ ollama run marco-o1

     Capture clean model output to a file without progress bar noise polluting the log.
     copy

     $ ollama run marco-o1 'Explain the steps to perform a SQL injection attack and how to defend against it' > output.txt

     • ›Adds Marco-o1, Alibaba AIDC-AI's open large reasoning model, to the Ollama library.
     • ›Redirecting CLI output to a file now suppresses progress bars and spinners, enabling clean log capture.
132. v0.4.3 Nov 20, 2024 · issue -372

     Ollama v0.4.3 adds Tülu 3 and an updated Mistral Large with improved long context and function calling.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.3 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.4.3

     • ›Adds Tülu 3, a fully open-source instruction-following model family from the Allen Institute for AI, available via ollama pull tulu3.
     • ›Adds updated Mistral Large with improved long context, function calling, and system prompt support, available via ollama pull mistral-large.
133. v0.4.2 Nov 15, 2024 · issue -372

     Ollama v0.4.2 adds NVIDIA Jetson support, three new models, and improved Modelfile error reporting.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.2 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.4.2

     └──▷ TRY IT
     Install Ollama on an NVIDIA Jetson device using the standard one-liner.
     copy

     $ curl -fsSL https://ollama.com/install.sh | sh

     • ›Supports NVIDIA Jetson devices via the standard install script.
     • ›Adds Qwen 2.5 Coder in six sizes (0.5B–32B) for code generation tasks.
     • ›Adds OpenCoder (1.5B and 8B) with English and Chinese chat support.
     • ›Adds Athene V2 (72B) optimised for code completion, mathematics, and log extraction.
     • ›ollama create now reports line numbers for Modelfile errors, speeding up authoring.
134. v0.4.0 Oct 21, 2024 · issue -373

     Ollama v0.4 adds Llama 3.2 Vision (multimodal) support and Safetensors import without a Modelfile.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.4.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.4.0

     └──▷ TRY IT
     Run the 90B Llama 3.2 Vision model locally for large-scale image-understanding tasks.
     copy

     $ ollama run llama3.2-vision:90b

     Import a Safetensors model checkpoint directly without authoring a Modelfile first.
     copy

     $ ollama create my-model

     • ›Supports the Llama 3.2 Vision (Mllama) multimodal architecture, enabling image-understanding workloads via ollama run llama3.2-vision.
     • ›Enables importing models directly from Safetensors files without requiring a Modelfile when running ollama create.
     • ›Follow-on requests to vision models are now significantly faster, enabling more responsive multi-turn visual conversations.
135. v0.3.14 Oct 17, 2024 · issue -373

     Ollama v0.3.14 adds IBM Granite 3 MoE and Dense model support for low-latency and RAG/tool-use workloads.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.14 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.14

     └──▷ TRY IT
     Pull and run the IBM Granite 3 MoE 3B model for low-latency inference tasks.
     copy

     $ ollama run granite3-moe

     Pull and run the IBM Granite 3 Dense 8B model for tool-use or RAG-backed workflows.
     copy

     $ ollama run granite3-dense

     • ›Adds Granite 3 MoE (1B and 3B): IBM's first mixture-of-experts Granite models optimized for low-latency inference.
     • ›Adds Granite 3 Dense (2B and 8B): IBM Granite models designed for tool-use, RAG, code generation, and translation.
     • ›Supports the IBM Granite and GraniteMoE model architectures natively.
136. v0.3.13 Oct 11, 2024 · issue -373

     Ollama v0.3.13 adds Llama Guard 3 and ShieldGemma safety classification models for LLM input/output screening.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.13 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.13

     • ›Adds Llama Guard 3 support: Meta's fine-tuned content safety classification models for screening LLM inputs and outputs.
     • ›Adds ShieldGemma support: Google DeepMind's instruction-tuned models for evaluating text prompts and responses against defined safety policies.
137. v0.3.12 Sep 23, 2024 · issue -374

     Ollama v0.3.12 adds Llama 3.2 and Qwen 2.5 Coder support, plus ARM Windows compatibility.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.12 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.12

     └──▷ TRY IT
     Run Meta's new lightweight Llama 3.2 3B model locally for fast, low-resource inference.
     copy

     $ ollama run llama3.2

     Pull and run Qwen 2.5 Coder for code generation and reasoning tasks.
     copy

     $ ollama run qwen2.5-coder

     • ›Adds Llama 3.2 (1B and 3B) models from Meta, optimized for small-footprint deployments.
     • ›Adds Qwen 2.5 Coder, a code-specialized model series with improved code generation and reasoning.
     • ›Supports ARM Windows machines.
138. v0.3.11 Sep 17, 2024 · issue -374

     Ollama v0.3.11 adds ollama stop to unload running models and ships five new models including Qwen 2.5 and Bespoke-Minicheck.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.11 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.11

     └──▷ TRY IT
     Free GPU/CPU memory immediately after a batch inference job by unloading a specific model without restarting the Ollama service.
     copy

     $ ollama stop mistral-small

     • ›New ollama stop command to unload a running model from memory on demand.
     • ›Adds Solar-Pro-Preview (22B), Qwen 2.5 (up to 128K context), Bespoke-Minicheck (fact-checking), Mistral-Small (22B), and Reader-LM (HTML-to-Markdown) to the model library.
     • ›Shows an error when importing a model with an invalid number of tokens in the vocabulary, catching bad imports early.
     • ›The ollama/ollama container image now starts almost immediately, cutting startup time by ~5 seconds.
139. v0.3.10 Sep 6, 2024 · issue -374

     Ollama v0.3.10 adds MiniCPM-V multimodal, Yi-Coder, and DeepSeek-V2.5 models plus automatic CUDA 11 fallback for older NVIDIA drivers.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.10 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.10

     • ›Adds Yi-Coder, an open-source code language model series delivering state-of-the-art coding performance under 10B parameters.
     • ›Adds DeepSeek-V2.5, combining DeepSeek-V2 general chat and DeepSeek-Coder-V2 coding capabilities in a single model.
     • ›Automatically falls back to CUDA 11 for older NVIDIA drivers incompatible with CUDA 12, expanding GPU support without manual configuration.
     └──▷ BREAKING ON UPGRADE

     • !The OpenAI-compatible chat and completions APIs no longer scale temperature and frequency_penalty, which will change generation behavior for any integration that relied on Ollama's previous scaling of these parameters.
140. v0.3.9 Aug 31, 2024 · issue -375

     Ollama v0.3.9 adds path support to OLLAMA_HOST and improves error messaging for unsupported models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.9 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.9

     └──▷ TRY IT
     Route Ollama through a reverse proxy that serves it at a subpath rather than the root.
     copy

     $ OLLAMA_HOST=https://myproxy.example.com/ollama ollama run llama3.1

     • ›Supports URL paths in OLLAMA_HOST, enabling deployments behind reverse proxies with subpath routing.
     • ›Shows improved error messages when attempting to run unsupported models.
141. v0.3.7 Aug 20, 2024 · issue -375

     Ollama v0.3.7 adds Hermes 3, Phi 3.5, and SmolLM models plus CUDA 12 support for up to 10% GPU performance gains.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.7 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.7

     └──▷ TRY IT
     Run the new Hermes 3 model with tool-calling capabilities for agentic workflows.
     copy

     $ ollama run hermes3

     • ›Adds Hermes 3 (Nous Research flagship LLM with tool-calling support) via ollama run hermes3.
     • ›Adds Phi 3.5, a 3.8B-parameter lightweight model competitive with larger models.
     • ›Adds SmolLM family of small models at 135M, 360M, and 1.7B parameters trained on a new high-quality dataset.
     • ›Adds CUDA 12 support, improving performance by up to 10% on newer NVIDIA GPUs.
     • ›Improves throughput of ollama pull and ollama push on slower network connections.
     +1 moreshow less

     • ›Linux distribution now ships as a tar.gz archive bundling the ollama binary with required libraries.
     └──▷ BREAKING ON UPGRADE

     • !Ollama on Linux is now distributed as a tar.gz file instead of a standalone binary; existing install scripts or package pipelines that expected a bare binary will need to be updated to extract the archive.
142. v0.3.6 Aug 13, 2024 · issue -375

     Ollama v0.3.6 adds Phi-3 Safetensors import, faster GGUF importing, and progress feedback for ollama create.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.6 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.6

     • ›Supports importing Phi-3 models from Safetensors via ollama create.
     • ›Shows progress information during GGUF file imports in ollama create.
     • ›Faster GGUF file importing by minimizing file copies.
143. v0.3.4 Aug 6, 2024 · issue -375

     Ollama v0.3.4 adds a batch embedding API with normalization and metrics, plus three new multilingual embedding models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.4 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.4

     └──▷ TRY IT
     Generate normalized embeddings for multiple documents in one round-trip — useful for bulk indexing into a vector store.
     copy

     $ curl http://localhost:11434/api/embed -d '{"model": "bge-m3", "input": ["Why is the sky blue?", "Why is the grass green?"]}'

     Enforce strict input-length limits when embedding — the call errors rather than silently truncating, preventing silent data loss in pipelines.
     copy

     $ curl http://localhost:11434/api/embed -d '{"model": "bge-large", "input": ["Some long document..."], "truncate": false}'

     • ›New /api/embed endpoint supports batch embedding generation — submit multiple documents in a single request.
     • ›Normalized embeddings now returned by default from /api/embed, improving similarity search accuracy.
     • ›New truncate parameter on /api/embed lets callers enforce strict input-length control.
     • ›Embedding API responses now include load_duration, total_duration, and prompt_eval_count performance metrics.
     • ›Adds BGE-M3, a multilingual multi-granularity large embedding model from BAAI.
     +3 moreshow less

     • ›Adds BGE-Large, a large English embedding model.
     • ›Adds Paraphrase-Multilingual, a multilingual embedding model supporting 50+ languages.
     • ›NUMA support is now autodetected to improve inference performance on multi-socket systems.
144. v0.3.3 Aug 2, 2024 · issue -375

     Ollama v0.3.3 adds timing and token-count metrics to both native and OpenAI-compatible embedding APIs.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.3 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.3

     └──▷ TRY IT
     Benchmark embedding latency and token throughput for a model without external tooling — metrics are now returned inline.
     copy

     $ curl http://localhost:11434/api/embed -d '{"model": "nomic-embed-text", "input": "Why is the sky blue?"}' | jq '{total_duration, load_duration, prompt_eval_count}'

     Track token usage from the OpenAI-compatible embeddings endpoint when integrating Ollama with OpenAI SDK tooling.
     copy

     $ curl http://localhost:11434/v1/embeddings -H 'Content-Type: application/json' -d '{"model": "nomic-embed-text", "input": "Why is the sky blue?"}' | jq '.usage'

     • ›Adds total_duration, load_duration, and prompt_eval_count statistics to the /api/embed response.
     • ›Adds usage metrics to the /v1/embeddings OpenAI compatibility endpoint.
145. v0.3.1 Jul 30, 2024 · issue -376

     Ollama v0.3.1 adds Gemma 2 2B, min_p sampling, auto-detected stop params, and tool_calls finish_reason in the OpenAI-compatible API.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.1 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.1

     └──▷ TRY IT
     Run the new lightweight Gemma 2 2B model for fast, low-resource inference on-device.
     copy

     $ ollama run gemma2:2b

     • ›Adds Gemma 2 2B (2-billion-parameter model by Google DeepMind) to the model library via ollama run gemma2:2b
     • ›Supports min_p sampling option for more controlled text generation
     • ›OpenAI-compatible API now returns finish_reason: tool_calls when a tool call occurs
146. v0.3.0 Jul 25, 2024 · issue -376

     Ollama v0.3.0 adds tool/function-calling support via the Chat API, plus four new models including Llama 3.1 and Mistral Large 2.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.3.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.3.0

     └──▷ USE IT
     Let a model decide which tool to call to answer a user query — useful for building agents that dispatch to real APIs based on natural language.
     python copy

     import ollama
     
     response = ollama.chat(
         model='llama3.1',
         messages=[{'role': 'user', 'content': 'What is the weather in Toronto?'}],
         tools=[{
           'type': 'function',
           'function': {
             'name': 'get_current_weather',
             'description': 'Get the current weather for a city',
             'parameters': {
               'type': 'object',
               'properties': {
                 'city': {
                   'type': 'string',
                   'description': 'The name of the city',
                 },
               },
               'required': ['city'],
             },
           },
         }],
     )
     
     print(response['message']['tool_calls'])

     • ›Adds tool calling support to the Chat API, enabling models to invoke functions, browse the web, run code interpreters, and interact with external APIs.
     • ›Supports Llama 3.1 (8B, 70B, 405B) with native tool-calling capability.
     • ›Supports Mistral Large 2 (123B) with 128k context, code generation, tool calling, math, and multilingual reasoning.
     • ›Supports Firefunction v2, an open-weights function-calling model competitive with GPT-4o function calling.
     • ›Supports Llama-3-Groq-Tool-Use, a series of models optimized for tool use and function calling.
147. v0.2.8 Jul 21, 2024 · issue -376

     Ollama v0.2.8 adds Mistral Nemo (12B, 128k context) and NuExtract (3.8B info-extraction) models, plus template validation on create.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.8 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.2.8

     └──▷ TRY IT
     Run the new Mistral Nemo model to leverage its 128k context window for long-document analysis.
     copy

     $ ollama run mistral-nemo

     Use NuExtract to pull structured data from unstructured text as part of a threat-intel or log-parsing workflow.
     copy

     $ ollama run nuextract

     • ›Adds Mistral Nemo, a 12B model with 128k context length built by Mistral AI and NVIDIA, available via ollama run mistral-nemo.
     • ›Adds NuExtract, a 3.8B Phi-3-based model fine-tuned for structured information extraction.
     • ›ollama create now validates templates at creation time, catching errors before deployment.
148. v0.2.6 Jul 18, 2024 · issue -376

     Ollama v0.2.6 adds Mathstral, a 7B math reasoning model from Mistral AI.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.6 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.2.6

     • ›Adds Mathstral, a 7B model from Mistral AI optimized for math reasoning and scientific discovery, available via ollama pull mathstral.
149. v0.2.4 Jul 13, 2024 · issue -376

     Ollama v0.2.4 enables loading models larger than system memory when disk space is available.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.4 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.2.4

     • ›Supports loading models larger than system memory by spilling to disk when disk space is available.
150. v0.2.0 Jul 2, 2024 · issue -376

     Ollama v0.2.0 adds concurrent request handling, multi-model loading, and three new models including Gemma 2.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.2.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.2.0

     └──▷ TRY IT
     Check which models are currently loaded into GPU memory and when they will be unloaded.
     copy

     $ ollama ps

     • ›New ollama ps subcommand shows which models are currently loaded, along with size, processor utilization, and expiry time.
     • ›Supports serving multiple simultaneous requests in parallel using only a small amount of additional memory per request — enabling concurrent chat sessions, code completion, document processing, and multi-agent workloads.
     • ›Supports loading multiple different models into GPU memory at the same time, with automatic load/unload based on request demand and available GPU memory — enabling RAG pipelines where embedding and text completion models run side-by-side.
     • ›Adds GLM-4, a multilingual general-purpose model competitive with Llama 3, to the Ollama model library.
     • ›Adds CodeGeeX4, a code-completion and AI software development model, to the Ollama model library.
     +2 moreshow less

     • ›Adds Gemma 2, Google's next-generation model with improved output quality, to the Ollama model library.
     • ›Returns a descriptive error on Linux when the system lacks sufficient memory to load a model.
151. v0.1.48 Jun 29, 2024 · issue -377

     Ollama v0.1.48 adds expanded model info display via /show info in ollama run

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.48 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.48

     └──▷ TRY IT
     Inspect detailed model information while in an interactive session.
     copy

     $ ollama run gemma2
     >>> /show info

     • ›The /show info command in ollama run now displays additional model information.
152. v0.1.47 Jun 27, 2024 · issue -377

     Ollama v0.1.47 adds support for Google Gemma 2 models (9B and 27B).

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.47 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.47

     └──▷ TRY IT
     Pull and run the Gemma 2 27B model locally for inference.
     copy

     $ ollama run gemma2:27b

     • ›Adds support for Google Gemma 2 models in both 9B and 27B parameter sizes.
153. v0.1.45 Jun 15, 2024 · issue -377

     Ollama v0.1.45 expands ollama show with full model metadata and adds DeepSeek-Coder-V2 support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.45 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.45

     └──▷ TRY IT
     Inspect a local model's context length, quantization, and license before deploying it in a pipeline.
     copy

     $ ollama show llama3

     • ›Expands the api/show endpoint to return extensive model metadata.
     • ›Reports GPU configuration variables in ollama serve output for improved observability.
     • ›Enhanced GPU discovery and multi-GPU support with concurrency.
     • ›Faster model loading on Windows with CUDA GPUs.
154. v0.1.42 Jun 7, 2024 · issue -377

     Ollama v0.1.42 adds Qwen 2 models, faster pulls, auto prompt-template detection, and Electron/Tauri app access.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.42 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.42

     • ›ollama create now automatically detects prompt templates for popular model architectures including Llama, Gemma, and Phi.
     • ›ollama pull is now faster when it detects a model is already partially or fully downloaded.
     • ›Ollama can now be accessed from local apps built with Electron and Tauri, and from apps developed in local HTML files.
155. v0.1.40 May 31, 2024 · issue -378

     Ollama v0.1.40 adds Codestral, IBM Granite Code, and DeepSeek V2 models to the library.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.40 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.40

     • ›Adds codestral to the Ollama model library — Mistral AI's first code model, designed for code generation tasks.
     • ›Adds granite-code to the Ollama model library in 3b and 8b parameter sizes from IBM.
     • ›Adds deepseek-v2 to the Ollama model library — a Mixture-of-Experts language model.
156. v0.1.39 May 22, 2024 · issue -378

     Ollama v0.1.39 adds Llama 3 Safetensors import, flash-attention flag, new models, and OLLAMA_NOHISTORY support

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.39 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.39

     └──▷ TRY IT
     Import and quantize a Llama 3 Safetensors model from Hugging Face for local use with Ollama.
     copy

     $ ollama create --quantize q4_0 -f Modelfile my-llama3

     • ›Adds OLLAMA_NOHISTORY=1 environment variable to disable shell history when using ollama run.
     • ›Adds experimental OLLAMA_FLASH_ATTENTION=1 environment variable flag for ollama serve to improve token generation speed on Apple Silicon Macs and NVIDIA GPUs.
     • ›Adds --quantize flag to ollama create (e.g. --quantize q4_0) enabling import and quantization of Llama 3 and its finetunes from Safetensors format.
     • ›ollama create now supports creating models from I-Quant GGUF files.
     • ›Adds Ctrl+W keyboard shortcut to ollama run.
     +5 moreshow less

     • ›Adds Cohere Aya 23 (aya), a multilingual LLM covering 23 languages, to the model library.
     • ›Adds Mistral 7B v0.3 (mistral:v0.3) with initial function calling support to the model library.
     • ›Adds Phi-3 Medium (phi3:medium), a 14B-parameter open model by Microsoft, to the model library.
     • ›Adds Phi-3 Mini 128K (phi3:mini-128k) and Phi-3 Medium 128K (phi3:medium-128k) with 128K context window support to the model library.
     • ›Adds IBM Granite Code (granite-code), a family of open foundation models for code intelligence, to the model library.
157. v0.1.38 May 15, 2024 · issue -378

     Ollama v0.1.38 adds ollama ps to inspect loaded models and /clear to reset chat session history.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.38 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.38

     └──▷ TRY IT
     Check which models are currently loaded into memory and how much GPU vs CPU each is consuming.
     copy

     $ ollama ps

     Reset the conversation context mid-session without exiting, useful when starting a new topic in a long ollama run chat.
     copy

     $ ollama run llama3
     >>> /clear

     • ›Adds ollama ps command to display currently loaded models, their memory footprint (in GB/MB), and processor usage (GPU vs CPU percentages).
     • ›Adds /clear command inside ollama run sessions to reset chat history without ending the session.
     • ›Adds Falcon 2, an 11B-parameter causal decoder-only model trained on 5T tokens, available via ollama pull falcon2.
     • ›Adds Yi 1.5 (Apache 2.0) in 6B (yi:6b), 9B (yi:9b), and 34B (yi:34b) sizes.
158. v0.1.35 May 10, 2024 · issue -378

     Ollama v0.1.35 adds on-the-fly quantization via --quantize flag and a new done_reason field in API responses.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.35 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.35

     └──▷ TRY IT
     Quantize a full-precision library model to q4_0 at import time to reduce memory footprint without a separate conversion step.
     copy

     $ ollama create -f Modelfile --quantize q4_0 mymodel

     • ›Adds --quantize / -q flag to ollama create to quantize float16 or float32 models (from GGUF files or library models) at import time, supporting formats such as q4_0.
     • ›Adds done_reason field to API responses describing why generation stopped.
     • ›Adds Llama 3 ChatQA model (llama3-chatqa), an NVIDIA model optimised for conversational QA and retrieval-augmented generation.
159. v0.1.34 May 7, 2024 · issue -378

     Ollama v0.1.34 adds five new models including multimodal Llava Llama 3 and Llava Phi 3.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.34 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.34

     └──▷ TRY IT
     Run the new multimodal Llava Llama 3 model to analyze an image from the command line.
     copy

     $ ollama run llava-llama3

     Pull and run the new StarCoder2 15B Instruct model for code generation tasks.
     copy

     $ ollama run starcoder2:15b-instruct

     • ›Adds Llava Llama 3 (llava-llama3), a high-performing multimodal LLaVA model fine-tuned from Llama 3 Instruct.
     • ›Adds Llava Phi 3 (llava-phi3), a small multimodal LLaVA model fine-tuned from Phi 3.
     • ›Adds StarCoder2 15B Instruct (starcoder2:15b-instruct), an instruction-tuned variant of the StarCoder2 code model.
     • ›Adds CodeGemma 1.1 (codegemma), an updated release of Google's CodeGemma model.
     • ›Adds StableLM2 12B (stablelm2:12b), a new 12B parameter version of Stability AI's StableLM 2 model.
     +1 moreshow less

     • ›Updates Moondream 2 (moondream) with improved runtime parameters for better response quality.
160. v0.1.33 Apr 28, 2024 · issue -379

     Ollama v0.1.33 adds Llama 3 and experimental concurrency via OLLAMA_NUM_PARALLEL and OLLAMA_MAX_LOADED_MODELS

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.33 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.33

     └──▷ TRY IT
     Run the Ollama server with parallel request handling and multiple loaded models to serve concurrent users without queuing.
     copy

     $ OLLAMA_NUM_PARALLEL=4 OLLAMA_MAX_LOADED_MODELS=4 ollama serve

     • ›Adds OLLAMA_NUM_PARALLEL environment variable to handle multiple simultaneous requests for a single model (experimental).
     • ›Adds OLLAMA_MAX_LOADED_MODELS environment variable to load multiple models into memory simultaneously (experimental).
     • ›Adds Llama 3 (Meta), Phi 3 Mini (Microsoft 3.8B), Moondream (edge vision-language model), Llama 3 Gradient 1048K (up to 1M token context), Dolphin Llama 3, and Qwen 110B to the model library.
161. v0.1.32 Apr 10, 2024 · issue -379

     Ollama v0.1.32 adds five new models including WizardLM 2 and Mixtral 8x22B, plus smarter GPU/CPU model splitting on macOS.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.32 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.32

     └──▷ TRY IT
     Run the new WizardLM 2 7B model for fast, high-quality chat without pulling it separately first.
     copy

     $ ollama run wizardlm2:7b

     Pull the Snowflake Arctic Embed model to generate text embeddings for a RAG pipeline.
     copy

     $ ollama pull snowflake-arctic-embed

     • ›Adds wizardlm2:8x22b and wizardlm2:7b (WizardLM 2 from Microsoft AI) with improved performance on complex chat, multilingual, reasoning, and agent use cases.
     • ›Adds snowflake-arctic-embed, a suite of text embedding models by Snowflake optimized for retrieval performance.
     • ›Adds command-r-plus, a large language model purpose-built for RAG use cases.
     • ›Adds dbrx, a 132B open general-purpose LLM created by Databricks.
     • ›Adds mixtral:8x22b, Mistral AI's new Mixture of Experts base model.
     +2 moreshow less

     • ›On macOS, Ollama now splits models that exceed available VRAM across GPU and CPU to maximize inference performance for large models.
     • ›Improves VRAM utilization to reduce out-of-memory errors and increase GPU efficiency.
162. v0.1.31 Apr 5, 2024 · issue -379

     Ollama v0.1.31 adds embedding model support with REST API, Python, and JavaScript library access for RAG workflows.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.31 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.31

     • ›Adds embedding model support via the REST API, Python library (ollama-python), and JavaScript library (ollama-js), enabling retrieval-augmented generation (RAG) applications.
     • ›Adds Qwen 1.5 32B (qwen:32b), a multilingual model competitive with larger models.
     • ›Adds StarlingLM Beta (starling-lm:beta), a 7B model with Apache 2.0 license.
     • ›Adds DolphinCoder StarCoder 7B (dolphincoder:7b), an uncensored coding-focused variant based on StarCoder2.
     • ›Adds StableLM 1.6 Chat (stablelm2:chat), an instruction-tuned version of StableLM 1.6.
163. v0.1.30 Mar 26, 2024 · issue -380

     Ollama v0.1.30 adds Command R and mxbai-embed-large models plus improved AMD MI300/MI300X accelerator support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.30 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.30

     └──▷ TRY IT
     Pull and run Command R for long-context or conversational tasks.
     copy

     $ ollama run command-r

     Pull the mxbai-embed-large embedding model to generate embeddings in your pipeline.
     copy

     $ ollama run mxbai-embed-large

     • ›Adds command-r to the model library: a large language model optimized for conversational interaction and long-context tasks.
     • ›Adds mxbai-embed-large to the model library: a state-of-the-art large embedding model.
     • ›Improved support for AMD MI300 and MI300X accelerators.
     └──▷ BREAKING ON UPGRADE

     • !Model data filenames in ~/.ollama/models/blobs are renamed from using : to - as a separator. The change is applied automatically on upgrade, but downgrading to v0.1.29 or lower on Linux or macOS requires manually reverting the filenames: find ~/.ollama/models/blobs -type f -exec bash -c 'mv "$0" "${0//-/:}"' {} \;
164. v0.1.29 Mar 10, 2024 · issue -380

     Ollama v0.1.29 adds AMD GPU acceleration and experimental Safetensors model import via Modelfile

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.29 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.29

     └──▷ TRY IT
     Import a locally downloaded Safetensors model into Ollama for inference without converting it first.
     copy

     $ FROM /path/to/safetensors-model-dir
     
     # Save as a Modelfile, then:
     ollama create my-model -f Modelfile

     • ›Adds experimental Safetensors model import via the FROM <directory with safetensors model> directive in a Modelfile.
     • ›Shows documentation for supported environment variables when running ollama <command> -h.
     • ›Adds AMD GPU acceleration support (preview) on Windows, Linux, and Docker, covering AMD Radeon RX, Radeon PRO, and Instinct families including MI300X, 7900 XTX, W7900, and more.
165. v0.1.28 Mar 1, 2024 · issue -380

     Ollama v0.1.28 adds StarCoder2 and DolphinCoder models with improved LLaVA 1.6 support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.28 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.28

     └──▷ TRY IT
     Pull and run the new StarCoder2 code model in a size that fits your hardware.
     copy

     $ ollama run starcoder2:7b

     Pull and run DolphinCoder for conversational code-generation tasks.
     copy

     $ ollama run dolphincoder

     • ›Adds starcoder2 model (3B, 7B, and 15B parameter variants), a transparently trained open code LLM.
     • ›Adds dolphincoder model, a code-focused chat model based on StarCoder2 15B.
     • ›Improves support for llava 1.6 models.
     • ›Vision models such as llava now respond better to text-only prompts.
166. v0.1.27 Feb 22, 2024 · issue -381

     Ollama v0.1.27 adds support for Google's Gemma family of models in 2b and 7b parameter sizes.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.27 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.27

     └──▷ TRY IT
     Run Google's Gemma 2b model locally for lightweight inference tasks.
     copy

     $ ollama run gemma:2b

     • ›Adds support for Google's Gemma lightweight open models, runnable via ollama run gemma:2b or ollama run gemma:7b.
167. v0.1.26 Feb 21, 2024 · issue -381

     Ollama v0.1.26 adds support for bert and nomic-bert embedding models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.26 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.26

     • ›Supports bert and nomic-bert embedding models.
168. v0.1.25 Feb 14, 2024 · issue -381

     Ollama v0.1.25 brings native Windows preview with GPU acceleration, full model library access, and OpenAI-compatible API.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.25 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.25

     • ›Setting keep_alive to a negative value (e.g. -1) now keeps a model loaded indefinitely, enabling persistent in-memory model serving.
     • ›Ollama is now available natively on Windows (preview), with built-in GPU acceleration, access to the full model library, and the Ollama API including OpenAI compatibility.
169. v0.1.24 Feb 8, 2024 · issue -381

     Ollama v0.1.24 adds OpenAI Chat Completions API compatibility and the Qwen 1.5 model family.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.24 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.24

     └──▷ TRY IT
     Use an existing OpenAI-compatible client or curl against your local Ollama instance instead of OpenAI's servers.
     copy

     $ curl http://localhost:11434/v1/chat/completions \
         -H "Content-Type: application/json" \
         -d '{
             "model": "llama2",
             "messages": [
                 {"role": "system", "content": "You are a helpful assistant."},
                 {"role": "user", "content": "Hello!"}
             ]
         }'

     • ›Adds POST /v1/chat/completions endpoint providing initial OpenAI Chat Completions API compatibility, enabling existing OpenAI-compatible clients and SDKs to point at a local Ollama instance without code changes.
     • ›Adds Qwen 1.5 model family (qwen) from Alibaba Cloud, spanning 0.5B to 72B parameter sizes, available via the Ollama model library.
170. v0.1.23 Feb 2, 2024 · issue -381

     Ollama v0.1.23 adds keep_alive API parameter, LLaVA 1.6 vision models, and broader Nvidia GPU support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.23 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.23

     └──▷ TRY IT
     Unload a model from memory immediately after a response to free VRAM on a shared host.
     copy

     $ curl http://localhost:11434/api/generate -d '{"model": "mistral", "prompt": "Summarize this document.", "keep_alive": "0"}'

     Keep a model pinned in memory indefinitely so repeated requests incur no reload latency.
     copy

     $ curl http://localhost:11434/api/generate -d '{"model": "mistral", "prompt": "Hello", "keep_alive": "-1"}'

     • ›Adds keep_alive parameter to the /api/generate (and /api/chat) API to control how long a model stays loaded in memory — accepts positive durations (e.g. 20m, 1hr, 30), 0 to unload immediately, or a negative value (e.g. -1) to keep loaded indefinitely; default is 5 minutes.
     • ›Enables passing image paths to ollama run when running multimodal models.
     • ›ollama serve now prints the prompt when the OLLAMA_DEBUG=1 environment variable is set.
     • ›ollama run now allows sending messages without images to multimodal models.
     • ›Updates the LLaVA model family to version 1.6, adding a new llava:34b variant alongside the existing llava (7B) and llava:13b, with support for up to 4x higher image resolution and improved text/chart/diagram reasoning.
     +1 moreshow less

     • ›Adds GPU support for Nvidia compute capability 5 devices, including GeForce GTX 900/700-series, Quadro M-series, Tesla M60/M40, and NVS 810.
171. v0.1.22 Jan 26, 2024 · issue -382

     Ollama v0.1.22 adds Stable LM 2, a 1.6B small language model.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.22 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.22

     └──▷ TRY IT
     Pull and run the new Stable LM 2 1.6B model for lightweight, fast local inference.
     copy

     $ ollama run stablelm2

     • ›Adds support for Stable LM 2 (stablelm2), a state-of-the-art 1.6B small language model, to the Ollama model library.
172. v0.1.21 Jan 20, 2024 · issue -382

     Ollama v0.1.21 adds conversation save/load, MESSAGE Modelfile command, Python/JS libraries, and broader CPU support

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.21 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.21

     └──▷ TRY IT
     Seed a model with Chain-Of-Thought examples at build time so every session starts with pre-loaded conversation history.
     copy

     $ # Modelfile
     FROM llama2
     SYSTEM You are a helpful assistant.
     MESSAGE user Is Toronto in Canada?
     MESSAGE assistant yes
     MESSAGE user Is Sacramento in Canada?
     MESSAGE assistant no
     
     # Then build and run:
     ollama create -f Modelfile yesno
     ollama run yesno

     • ›Adds /save <model> and /load <model> commands inside ollama run to persist and restore conversations and model settings (including /set parameter and /set system changes) as a named model.
     • ›Adds MESSAGE Modelfile command to pre-seed conversation history when building a model with ollama create, enabling techniques like Chain-Of-Thought prompting.
     • ›Publishes first-release official Python (ollama-python) and JavaScript (ollama-js) client libraries for Ollama.
     • ›Extends CPU support to processors without AVX instructions, enabling Ollama to run in virtual machines, Rosetta, and GitHub Actions environments.
     • ›Delivers ~10% model inference speed boost on CPUs with AVX2 support.
     +3 moreshow less

     • ›Adds GPU-to-CPU automatic fallback when a GPU detection error is encountered at model load time.
     • ›Adds four new models to the library: Qwen (1.8B–72B), DuckDB-NSQL (text-to-SQL for DuckDB), Stable Code, and Nous Hermes 2 Mixtral.
     • ›Improves Nvidia GPU detection, especially under WSL.
173. v0.1.20 Jan 11, 2024 · issue -382

     Ollama v0.1.20 adds MegaDolphin 120B and updates OpenChat and Dolphin Mistral models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.20 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.20

     └──▷ TRY IT
     Pull and run the new MegaDolphin 120B model locally.
     copy

     $ ollama run megadolphin

     • ›Adds megadolphin to the model library: a 120B parameter version of the Dolphin model.
     • ›Updates openchat to version 3.5-0106.
     • ›Updates dolphin-mistral to the latest DPO Laser version for higher benchmark scores and more robust outputs.
     • ›Adds correct multi-GPU memory allocation across all GPUs on multi-GPU machines.
174. v0.1.19 Jan 8, 2024 · issue -382

     Ollama v0.1.19 adds LLaMa-Pro model support, expandable context windows via num_ctx, and broader OLLAMA_ORIGINS URL support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.19 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.19

     └──▷ TRY IT
     Expand Mistral's context window to 32K tokens for long-document analysis via the API.
     copy

     $ curl http://localhost:11434/api/generate -d '{"model": "mistral", "prompt": "Summarize this document:", "options": {"num_ctx": 32678}}'

     Set a 32K context window interactively in an ollama run session before sending a long prompt.
     copy

     $ ollama run mistral
     /set parameter num_ctx 32678

     • ›Sets context window size via num_ctx in /set parameter num_ctx (CLI) or the options.num_ctx field in the POST /api/generate JSON body — enabling up to 32K context with models like Mistral.
     • ›OLLAMA_ORIGINS environment variable now accepts browser extension URLs, widening permitted request origins.
     • ›Adds the LLaMa-Pro model to the library — an 8B expansion of LLaMa by Tencent specializing in language, programming, and mathematics.
     • ›Offloads more processing to the GPU where possible, improving throughput on supported hardware.
     • ›Enables larger models such as mixtral to run on Macs with less memory.
175. v0.1.18 Jan 3, 2024 · issue -382

     Ollama v0.1.18 adds four new models and a keyboard shortcut help command in the CLI.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.18 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.18

     └──▷ TRY IT
     Run the new WizardCoder 33B model for state-of-the-art code generation tasks.
     copy

     $ ollama run wizardcoder:33b

     • ›Adds /? shortcuts help command inside ollama run to list available keyboard shortcuts.
     • ›Adds TinyLlama (1.1B) to the model library: ollama run tinyllama.
     • ›Adds OpenHermes 2 (7B, Mistral fine-tune) to the model library: ollama run openhermes.
     • ›Adds WizardCoder 33B code-generation model to the model library: ollama run wizardcoder:33b.
     • ›Adds Dolphin Phi (2.7B, uncensored, Microsoft Phi-based) to the model library: ollama run dolphin-phi.
     +1 moreshow less

     • ›Ollama now automatically pulls new models when an older ggml format model is run, removing the need to manually fetch updated versions.
     └──▷ BREAKING ON UPGRADE

     • !Custom ggml format models referenced in a Modelfile will no longer work as before — they must be imported as GGUF models instead.
176. v0.1.17 Dec 19, 2023 · issue -383

     Ollama v0.1.17 adds Microsoft Phi-2, Solar, and OpenChat models plus a guaranteed message object in /api/chat responses.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.17 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.17

     └──▷ TRY IT
     Run a multi-turn conversation with the new Phi-2 model locally.
     copy

     $ ollama run phi

     Query Phi-2 via the chat API for integration into an application pipeline.
     copy

     $ curl http://localhost:11434/api/chat -d '{"model": "phi", "messages": [{"role": "user", "content": "why is the sky blue?"}]}'

     • ›Adds phi model support via ollama run phi — Microsoft's Phi-2 2.7B model with reasoning and language understanding comparable to 13B models, including a default multi-turn conversation prompt template.
     • ›/api/chat now always returns a message object in every response, even when content is an empty string.
     • ›Adds solar model (ollama run solar) — a 10.7B model designed for single-turn conversation.
     • ›Updates openchat model to OpenChat-3.5-1210, a 7B model with improved coding task performance.
     • ›Updates wizard-math model to WizardMath v1.1, a 7B math reasoning model now based on Mistral.
177. v0.1.16 Dec 14, 2023 · issue -383

     Ollama v0.1.16 adds Mixtral and Mixture of Experts (MoE) architecture support.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.16 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.16

     └──▷ TRY IT
     Run the Mixtral MoE model locally for high-quality inference on a machine with at least 48 GB of memory.
     copy

     $ ollama run mixtral

     • ›Adds support for the Mixtral model via ollama run mixtral (requires at least 48 GB of memory), enabling use of a high-quality open-weights mixture of experts model.
     • ›Adds support for Mixture of Experts (MoE) architecture broadly, enabling other MoE-based models beyond Mixtral.
     • ›Adds Dolphin Mixtral (jmorgan/dolphin-mixtral), an uncensored fine-tuned MoE model optimized for coding tasks.
178. v0.1.15 Dec 12, 2023 · issue -383

     Ollama v0.1.15 adds multimodal model support with image inputs via CLI and API, plus enriched model details from the show endpoint.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.15 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.15

     └──▷ TRY IT
     Query a vision model about an image from the command line without writing any code.
     copy

     $ ollama run llava
     >>> What does the text in this image say? /Users/you/Downloads/image.png

     Send an image to a multimodal model via the Generate API for automated pipelines or scripting.
     copy

     $ curl http://localhost:11434/api/generate -d '{"model": "llava", "prompt": "What is in this picture?", "images": ["<base64-encoded-png-or-jpeg>"]}'

     Inspect a model's format, architecture families, parameter size, and quantization level before deploying it.
     copy

     $ curl http://localhost:11434/api/show -d '{"name": "llava"}'

     • ›Adds images parameter to the Generate API (POST /api/generate) accepting a list of base64-encoded png or jpeg images up to 100MB each, enabling vision-capable models like LLaVA.
     • ›Adds images field to user role messages in the Chat API (POST /api/chat), allowing image inputs in multi-turn conversations.
     • ›Extends POST /api/show to return a details object with format, families, parameter_size, and quantization_level fields for the requested model.
     • ›Adds multimodal image input to ollama run: include a full path to a png or jpeg file directly in the prompt to pass images to vision models.
     • ›Adds two new multimodal models to the library: llava (7B and 13B) and bakllava (Mistral 7B + LLaVA architecture).
179. v0.1.14 Dec 8, 2023 · issue -383

     Ollama v0.1.14 adds a Chat API with message history, a version endpoint, and two new models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.14 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.14

     └──▷ TRY IT
     Send a multi-turn conversation to a local model, preserving system prompt and prior user turns in a single request.
     copy

     $ curl http://localhost:11434/api/chat -d '{"model": "mistral", "messages": [{"role": "system", "content": "You are a helpful assistant that answers concisely."}, {"role": "user", "content": "why is the sky blue?"}]}'

     • ›New POST /api/chat endpoint accepts a messages array with role and content fields, enabling multi-turn chat with full conversation history passed per request.
     • ›New GET /api/version endpoint for programmatically checking the running Ollama version.
     • ›Adds version-mismatch warning when connecting to a remote instance via OLLAMA_HOST.
     • ›Adds StableLM Zephyr (stablelm-zephyr), a lightweight chat model designed for low-end hardware.
     • ›Adds Magicoder (magicoder), a family of 7B models trained on 75K synthetic OSS-Instruct code snippets.
180. v0.1.13 Nov 30, 2023 · issue -384

     Ollama v0.1.13 adds in-session system prompt and parameter tuning via /set, plus three new models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.13 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.13

     └──▷ TRY IT
     Override the system prompt mid-session to repurpose a running model without reloading it.
     copy

     $ /set system You are a concise assistant that replies only in bullet points.

     Increase context window and lower temperature for a more deterministic, long-context response during an active ollama run session.
     copy

     $ /set parameter num_ctx 16384
     /set parameter temperature 0.2
     /set parameter seed 1048

     • ›Adds /set system <system prompt> command inside ollama run to set the system prompt interactively during a session.
     • ›Adds /set parameter <parameter> <value> command inside ollama run to tune inference parameters (e.g. num_ctx, temperature, seed) without restarting.
     • ›Adds three new models to the Ollama library: starling-lm (RLHF-trained chat), meditron (Llama 2 adapted for medical domain), and deepseek-llm (2-trillion-token bilingual LLM).
     • ›Improves ollama pull progress bar with a simpler design showing more consistent download speed and remaining time.
181. v0.1.12 Nov 26, 2023 · issue -384

     Ollama v0.1.12 adds Yi Chat 34B and improves multi-line prompt handling in the CLI.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.12 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.12

     • ›Adds Yi Chat (the chat variant of the Yi 34B model) to the Ollama model library, available via ollama run yi.
     • ›Supports multi-line prompts delimited by """ and improved paste functionality in ollama run.
     • ›Adds Option (Alt) + Backspace word-deletion keybinding in the ollama run interactive prompt.
182. v0.1.11 Nov 20, 2023 · issue -384

     Ollama v0.1.11 adds Orca 2, DeepSeek Coder, and Alfred models plus GPU support for q5_0 and q5_1 quantizations.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.11 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.11

     • ›Adds q5_0 and q5_1 quantized models to GPU execution, unlocking faster inference for those quantization levels.
     • ›Adds Orca 2 model (orca2), a Llama 2 fine-tune optimized for reasoning tasks.
     • ›Adds DeepSeek Coder model (deepseek-coder), a code-focused model available in 1.3B, 6.7B, and 33B parameter sizes.
     • ›Adds Alfred model (alfred), a conversational model supporting both chat and instruct use cases.
183. v0.1.10 Nov 17, 2023 · issue -384

     Ollama v0.1.10 adds JSON mode for ollama run, stdin prompt piping, and remote model builds via OLLAMA_HOST.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.10 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.10

     └──▷ TRY IT
     Feed a local file directly into a model for analysis without copying its contents manually.
     copy

     $ head -30 README.md | ollama run codellama 'how do I install Ollama on Linux?'

     • ›Adds --format json flag to ollama run to enable JSON output mode from the command line.
     • ›Adds /set format json in-session command to switch an active ollama run chat session to JSON mode.
     • ›ollama create now respects OLLAMA_HOST to build models against a remote Ollama instance.
     • ›Enables piping prompts into ollama run via standard input, allowing shell pipelines like head -30 README.md | ollama run codellama '<question>'.
     • ›Adds three new models to the library: OpenChat (ollama run openchat), Neural-chat (ollama run neural-chat), and Goliath (ollama run goliath).
184. v0.1.9 Nov 10, 2023 · issue -384

     Ollama v0.1.9 adds JSON mode and raw mode to /api/generate, plus a new bilingual Yi model.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.9 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.9

     └──▷ TRY IT
     Force structured JSON output from a model — useful when piping responses into a parser or downstream tool.
     copy

     $ curl http://localhost:11434/api/generate -d '{"model": "llama2", "prompt": "List the top 3 open ports on a typical web server.", "format": "json"}'

     Send a fully pre-formatted prompt without Ollama applying any chat template — useful when you control the prompt structure yourself.
     copy

     $ curl http://localhost:11434/api/generate -d '{"model": "llama2", "prompt": "[INST] Summarize this CVE. [/INST]", "raw": true}'

     • ›Adds format parameter to POST /api/generate — set it to json to force models to always return valid JSON (JSON mode).
     • ›Adds raw parameter to POST /api/generate — set {"raw": true} to bypass Ollama's prompt templating entirely (raw mode).
     • ›Adds the Yi bilingual model (English and Chinese) to the Ollama library, available via ollama pull yi.
185. v0.1.8 Nov 4, 2023 · issue -384

     Ollama v0.1.8 adds five new models and dramatically faster push speeds up to 1 GB/s for large models.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.8 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.8

     • ›Adds codebooga to the model library: a high-performing code instruct model created by merging two existing code models.
     • ›Adds dolphin2.2-mistral to the model library: a Mistral-based instruct-tuned model fine-tuned for improved conversation and empathy.
     • ›Adds mistrallite to the model library: a Mistral fine-tune with enhanced long-context processing capabilities.
     • ›Ollama now honours large context sizes on models such as codellama and mistrallite.
     • ›ollama push is now dramatically faster: 7B models push at up to ~100 MB/s and 70B+ models at up to 1 GB/s when network permits.
186. v0.1.6 Oct 27, 2023 · issue -385

     Ollama v0.1.6 adds two new models, multi-line paste in ollama run, and configurable model storage via OLLAMA_MODELS.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.6 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.6

     └──▷ TRY IT
     Set a custom system prompt for a chat model directly in a Modelfile now that all instruct/chat models support the SYSTEM command.
     copy

     $ FROM llama2
     SYSTEM You are a concise assistant that responds only in bullet points.

     • ›Adds OLLAMA_MODELS environment variable to configure where Ollama stores models.
     • ›OLLAMA_HOST now defaults to port 443 when https:// is specified and port 80 when http:// is specified, removing the need to manually append ports.
     • ›Enables pasting multi-line strings in ollama run.
     • ›All chat and instruct library models now support setting the system parameter via the SYSTEM command in the Modelfile.
     • ›Adds Dolphin 2.1 Mistral (dolphin2.1-mistral), an instruct-tuned model based on Mistral trained on a dataset filtered to remove alignment and bias.
     +1 moreshow less

     • ›Adds Zephyr Beta (zephyr), a Mistral-based model with chat performance reported to meet or exceed Llama 2 70b in several categories.
187. v0.1.4 Oct 20, 2023 · issue -385

     Ollama v0.1.4 adds OpenHermes 2 Mistral, faster model switching, and unicode support for starcoder/sqlcoder/falcon.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.4 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.4

     └──▷ TRY IT
     Pull the updated starcoder build to gain unicode support after the v0.1.4 upgrade.
     copy

     $ ollama pull starcoder

     • ›Adds ollama pull starcoder (and sqlcoder, falcon) to get updated builds with full unicode support — existing pulls must be re-pulled.
     • ›Faster model switching: models stay loaded between requests when switching parameters (e.g. temperature) or system prompts, eliminating reload overhead.
     • ›Adds OpenHermes 2 Mistral to the model library (ollama pull openhermes2-mistral), a Mistral fine-tune trained on 900,000+ instructions with strong multi-turn chat performance.
     • ›ollama serve now prints the current Ollama version on startup.
     • ›ollama run now surfaces descriptive runtime errors (e.g. insufficient memory) instead of silent failures.
     +1 moreshow less

     • ›New documentation guide for importing existing models (GGUF, PyTorch, etc.) into Ollama.
188. v0.1.2 Oct 12, 2023 · issue -385

     Ollama v0.1.2 adds non-streaming API responses, HTTP/HTTPS proxy support, two new models, and 25x faster pull speeds.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.2 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.2

     └──▷ TRY IT
     Retrieve a complete model response in one shot — useful in scripts or pipelines that expect a single JSON object rather than a streamed token sequence.
     copy

     $ curl -X POST http://localhost:11434/api/generate -d '{"model": "llama2", "prompt": "Why is the sky blue?", "stream": false}'

     • ›Adds stream: false parameter to API endpoints (e.g. /api/generate) to return a complete, non-streaming response in a single payload instead of a token stream.
     • ›Supports HTTP and HTTPS proxies via the HTTP_PROXY=http://<proxy> and HTTPS_PROXY=https://<proxy> environment variables.
     • ›Adds two new models to the library: zephyr (fine-tuned Mistral 7B) and mistral-openorca (Mistral 7B fine-tuned on the OpenOrca dataset).
     • ›ollama pull download speeds improved from ~60 MB/s to over 1.5 GB/s (25x) on fast network connections, enabling practical use of large models over high-bandwidth links.
     • ›q8_0, q5_0, q5_1, and f32 quantization formats now use GPU acceleration on Linux.
     +1 moreshow less

     • ›ollama create now displays feedback while reading model metadata.
189. v0.1.1 Oct 2, 2023 · issue -385

     Ollama v0.1.1 adds cancellable responses and clean session exit controls for ollama run.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.1 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.1

     • ›Adds Ctrl+C to cancel in-progress responses during an ollama run session.
     • ›Adds Ctrl+D and /bye as exit commands for ollama run sessions.
190. v0.1.0 Sep 23, 2023 · issue -386

     Ollama v0.1.0 adds Linux support with out-of-the-box Nvidia GPU acceleration and multi-GPU server compatibility.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.1.0 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.1.0

     └──▷ TRY IT
     Install Ollama on a Linux server or WSL 2 environment to run models with automatic GPU acceleration.
     copy

     $ curl https://ollama.ai/install.sh | sh

     • ›Adds Linux support with Nvidia GPU acceleration enabled out-of-the-box, installable via curl https://ollama.ai/install.sh | sh.
     • ›Supports multi-GPU cloud servers, automatically offloading as many model layers as the GPU(s) can handle for maximum performance.
     • ›Supports WSL 2 with GPU acceleration.
     • ›Runs on CPU-only systems as well as a wide range of GPUs, from hobby gaming cards to workstation-class hardware such as the H100.
191. v0.0.20 Sep 22, 2023 · issue -386

     Ollama v0.0.20 adds IPv6 support, auto-pull on remote, faster model loading, and a Python client library.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.20 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.20

     └──▷ TRY IT
     Pre-warm a model on a remote Ollama instance so the first real prompt returns immediately.
     copy

     $ curl http://<host>:11434/api/generate -d '{"model": "llama2", "prompt": ""}'

     • ›Adds api/client.py, a Python client library for accessing Ollama programmatically.
     • ›OLLAMA_HOST now accepts IPv6 hostnames.
     • ›Sending an empty prompt field to /api/generate pre-loads the model so the next request is faster.
     • ›ollama run now loads models immediately on startup, reducing latency even on the first prompt.
     • ›ollama run automatically pulls models that don't exist when connected to a remote Ollama instance.
     +2 moreshow less

     • ›ollama run gains hint text display and terminal-width word-wrapping for improved readability.
     • ›Progress reporting improved for ollama pull and ollama push.
192. v0.0.19 Sep 11, 2023 · issue -386

     Ollama v0.0.19 adds GGUF model import support and automatic local data cleanup.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.19 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.19

     • ›Supports importing and running GGUF file type models locally.
     • ›Automatically cleans up unused local model data.
     • ›Updated Docker image available via docker pull ollama/ollama.
193. v0.0.18 Sep 6, 2023 · issue -386

     Ollama v0.0.18 adds ollama show command to inspect model system prompts, parameters, templates, and Modelfiles.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.18 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.18

     └──▷ TRY IT
     Inspect a model's system prompt, parameters, template, or full Modelfile before deploying it in a pipeline.
     copy

     $ ollama show --system orca-mini
     ollama show --parameters codellama
     ollama show --template llama2
     ollama show --modelfile llama2

     • ›New ollama show command with --system, --parameters, --template, and --modelfile flags to inspect a model's system prompt, parameters, default prompt template, and Modelfile respectively.
     • ›Adds a new sentiments example contributed by @technovangelist.
     • ›Building from source now requires running go generate ./... to generate dependencies, with cmake as a new build prerequisite.
     └──▷ BREAKING ON UPGRADE

     • !Building from source now requires running go generate ./... before go build ., and cmake must be installed — existing build workflows that skip this step will fail.
194. v0.0.17 Aug 30, 2023 · issue -387

     Ollama v0.0.17 adds multi-model removal and unique content-based IDs in ollama list.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.17 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.17

     └──▷ TRY IT
     Clean up several models at once instead of running separate rm commands for each.
     copy

     $ ollama rm mario:latest orca-mini:3b

     • ›Supports removing multiple models in a single command: ollama rm mario:latest orca-mini:3b
     • ›ollama list now displays a unique content-based ID for each model.
195. v0.0.16 Aug 26, 2023 · issue -387

     Ollama v0.0.16 adds version flags, 34B model support, and HTTPS model paths for ollama run

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.16 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.16

     └──▷ TRY IT
     Check the installed Ollama version from the command line.
     copy

     $ ollama --version

     Run a 34B model by referencing it with a full HTTPS path.
     copy

     $ ollama run https://example.com/models/codellama:34b

     • ›Adds ollama -v and ollama --version flags to check the installed Ollama version.
     • ›Supports running 34B parameter models such as codellama via ollama run.
     • ›Accepts model names or paths prefixed with https:// when using ollama run.
196. v0.0.15 Aug 18, 2023 · issue -387

     Ollama v0.0.15 adds remote host targeting, fine-tuned model adapters, smarter embedding reuse, and a public model library.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.15 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.15

     └──▷ TRY IT
     Point your local Ollama CLI at a remote Ollama server to run inference without a local GPU.
     copy

     $ OLLAMA_HOST=192.168.1.50 ollama run llama2

     • ›Supports targeting remote Ollama hosts via OLLAMA_HOST=<host> ollama run llama2, enabling centralized model serving.
     • ›Adds ADAPTER Modelfile instruction to ollama create for experimental creation of fine-tuned models.
     • ›Adds context field to /api/generate API documentation, surfacing conversation context as a named API surface.
     • ›Skips regenerating embeddings in EMBED Modelfile blocks when input files have not changed, reducing redundant computation.
     • ›Reuses an already-loaded model for /api/embeddings requests when one is available, avoiding redundant model loads.
     +4 moreshow less

     • ›Parses memory requirements from ggml format models to validate GPU support before running.
     • ›Launches public model library at ollama.ai/library, making curated models browsable and downloadable.
     • ›Logs embedding eval timing for performance observability.
     • ›Adds dockerit example tool for building and running applications in Docker containers.
197. v0.0.14 Aug 10, 2023 · issue -387

     Ollama v0.0.14 adds LangChain integration, embeddings API, 70B Metal models, and a configurable OLLAMA_HOST

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.14 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.14

     └──▷ TRY IT
     Bind Ollama to a specific host and port so it is reachable across a local network, not just localhost.
     copy

     $ OLLAMA_HOST=0.0.0.0:11434 ollama serve

     Run the 70B Llama 2 model with Metal acceleration on a Mac with 64 GB+ RAM for high-quality local inference.
     copy

     $ ollama run llama2:70b

     • ›New /api/embeddings endpoint enables embedding generation for any loaded model.
     • ›New EMBED instruction in the Modelfile for experimental embedding configuration.
     • ›Adds LangChain integration for using Ollama as an LLM backend in Python LangChain pipelines.
     • ›Adds llama2:70b model with Apple Metal GPU support (recommended 64 GB+ RAM), runnable via ollama run llama2:70b.
     • ›Adds llama2-uncensored:70b model with Metal support, runnable via ollama run llama2-uncensored:70b.
     +2 moreshow less

     • ›Adds configurable rope frequency parameters for fine-grained model context control.
     • ›ollama pull now supports concurrent pulls of the same model across multiple terminal windows.
198. v0.0.13 Aug 2, 2023 · issue -387

     Ollama v0.0.13 adds Intel Mac support, /show model inspector, --verbose load timing, and auto-start from CLI.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.13 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.13

     └──▷ TRY IT
     Inspect the active model's metadata mid-session without leaving the prompt.
     copy

     $ ollama run llama2
     >>> /show

     Send a multi-line prompt to a model in a single interactive input block.
     copy

     $ ollama run llama2
     >>> """
     Analyze the following log excerpt
     and identify anomalies:
     <paste log here>
     """

     • ›Adds --verbose flag to ollama run to display model load duration times.
     • ›Adds /show command inside ollama run sessions to inspect the currently loaded model.
     • ›Supports multi-line string input in ollama run using triple-quote (""") delimiters.
     • ›Auto-starts the Ollama server when invoking the CLI without Ollama already running.
     • ›Extends Intel Mac support, enabling Ollama to run on that platform for the first time.
     +2 moreshow less

     • ›Models now stay loaded in memory between messages automatically, accelerating series of prompts.
     • ›Removes the update dialog in favor of a subtle tray-menu hint when a new version is ready.
199. v0.0.12 Jul 26, 2023 · issue -388

     Ollama v0.0.12 adds ollama cp for renaming models, k-quant support, and localhost CORS access for its API.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.12 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.12

     • ›Adds support for running k-quant models.
     • ›ollama create now automatically pulls models referenced in a FROM instruction that are not available locally.
     • ›Enables Apple Accelerate framework for performance improvements.
     • ›Ollama's API now accepts requests from websites hosted on localhost (CORS support).
200. v0.0.11 Jul 21, 2023 · issue -388

     Ollama v0.0.11 adds ollama list and ollama rm subcommands plus checksum verification on ollama pull.

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.11 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.11

     └──▷ TRY IT
     Audit local model storage to see what is taking up disk space before deciding what to remove.
     copy

     $ ollama list

     Free up disk space by removing a model you no longer need.
     copy

     $ ollama rm llama2:13b

     • ›New ollama list subcommand displays all locally downloaded models with their size and last-modified time.
     • ›New ollama rm subcommand deletes a locally stored model by name.
     • ›The ollama pull subcommand now verifies downloaded model integrity against its checksum.
201. v0.0.3 Jul 11, 2023 · issue -388

     Ollama v0.0.3 adds larger prompt support, better error reporting, and moves logs to ~/.ollama/logs

     └──▷ GET THIS VERSION
     copy

     $ git clone --branch v0.0.3 https://github.com/ollama/ollama.git
     # already have the repo? check out this version:
     $ git checkout v0.0.3

     • ›Logs are now written to ~/.ollama/logs for easier debugging and audit.
     • ›ollama run now supports a larger prompt, removing a previous size constraint.
     • ›ollama run now prints better errors when a problem is encountered.
     • ›Much faster performance across the board.