| v0.40.11 | ## Speech Ollama can now generate [speech](https://docs.ollama.com/capabilities/speech) on macOS. `ollama run` plays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through the OpenAI-compatible `/v1/audio/speech` endpoint. ```sh ollama run phonon "Hello from Ollama." ``` ## d3 decision models [d3](https://ollama.com/library/d3) brings vLLM Semantic Router's decision models to Ollama. Give a model text, structured state, or an image, and ask | High | 10/24/2026 |
| v0.40.10 | ## NVIDIA Nemotron 3.5 Bolt E4B [Nemotron 3.5 Bolt E4B](https://ollama.com/library/nemotron-3.5-bolt) is NVIDIA’s smaller, Gemma 4-based vision-language model for fast local conversations, image understanding, and tool use. It supports a 128K-token context window. The model includes a DFlash draft for speculative decoding. ollama run nemotron-3.5-bolt:e4b **Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.9...v0.40.10 | High | 10/23/2026 |
| v0.40.9 | ## Speech Ollama can now generate [speech](https://docs.ollama.com/capabilities/speech) with Phonon on Apple Silicon. `ollama run` plays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through the OpenAI-compatible `/v1/audio/speech` endpoint. ```sh ollama run phonon "Hello from Ollama." ``` ## d3 decision models [d3](https://ollama.com/library/d3) brings vLLM Semantic Router's decision models to Ollama. Give a model text, structured state, o | High | 10/22/2026 |
| v0.40.8 | <p align="center"><img width="160" alt="flint-logo" src="https://github.com/user-attachments/assets/3c1741a5-710c-4bde-8ac7-096e40b495bb" /></p> ## Recursive Flint [Flint](https://ollama.com/library/flint) brings Recursive's coding model to Ollama. It is designed for the work coding agents do across a repository: understanding unfamiliar code, tracing bugs, implementing features, and adding tests. Reasoning, multi-turn tool use, and a 262K-token context window support longer tasks across f | High | 10/21/2026 |
| v0.40.6 | ## What's Changed * win: prevent orphaned runners by @dhiltgen in https://github.com/ollama/ollama/pull/18500 * gguf: add the q2_0 tensor and file types by @jmorganca in https://github.com/ollama/ollama/pull/18967 * Launch clef in Ollama's cloud by @jberg5 in https://github.com/ollama/ollama/pull/19036 * use identifiers for --ask mode question keys by @jberg5 in https://github.com/ollama/ollama/pull/19041 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.5...v0.40.6-rc0 | High | 10/16/2026 |
| v0.40.5 | ## NVIDIA Nemotron 3.5 Super [NVIDIA Nemotron 3.5 Super](https://ollama.com/library/nemotron-3.5-super) is a vision-language model for coding, reasoning, tool use, and document understanding. It pairs a 120B-parameter hybrid Mamba-2/Transformer mixture-of-experts backbone (12B active per token) with a C-RADIO vision encoder, and supports tool calling, an on/off thinking mode, and context up to 1M tokens. ``` ollama run nemotron-3.5-super ``` A compact sibling, [Nemotron 3.5 Bolt](http | High | 10/14/2026 |
| v0.40.4 | ## Decision models in the CLI Decision models can now be used directly from the terminal with `ollama run` — ask yes/no questions, classify text into labels, or score against a rubric: `ollama run nimble --ask "Is a refund being requested?" < ticket.txt` ## What's Changed * Kev decision models are now supported by the MLX runner on Apple silicon * `ollama launch` can now be used with usage credits without upgrading to a paid plan * `ollama launch codex` now includes locally instal | High | 10/12/2026 |
| v0.40.3 | ## What's Changed * `ollama launch claude` no longer shows a warning about Claude connectors by @hoyyeva in https://github.com/ollama/ollama/pull/18878 * `ollama launch codex` no longer warns about service tiers by @hoyyeva in https://github.com/ollama/ollama/pull/18879 * Paused background model upgrade for embedding and other request performance, by @jmorganca in https://github.com/ollama/ollama/pull/18908 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.40.2...v0.40.3 | High | 10/11/2026 |
| v0.40.2 | ## Model upgrades Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility when running on llama.cpp. To make downgrading safe, Ollama keeps the original copy as a backup, so upgraded models are temporarily kept on disk. A future release will remove these backups automatically. To remove backed up models now (requires `jq`): ```shell curl -s localhost:11434/api/tags | jq -r '.models[].name' | High | 10/8/2026 |
| v0.40.1 | ## What's Changed * server: proxy cloud usage and balance APIs by @drifkin in https://github.com/ollama/ollama/pull/18829 * llama: fix clef head reads past 2GiB on windows by @Gigrise in https://github.com/ollama/ollama/pull/18777 * cmd: remove account step from CLI onboarding by @hoyyeva in https://github.com/ollama/ollama/pull/18826 * manifest: avoid symlinks on Windows by @dhiltgen in https://github.com/ollama/ollama/pull/18852 * docs: fix 6 dead links in README community integrations li | High | 10/7/2026 |
| v0.35.1 | ## Clef decision models Ollama now supports [Clef](https://ollama.com/library/clef) and [Clef Flash](https://ollama.com/library/clef), Cloudflare's new open-source decision models, through `/v1/systemone`. Clef (27B) and Clef Flash (9B) are multimodal: requests can now include images alongside the text state, shared by all questions and scored jointly with it. ```sh curl http://localhost:11434/v1/systemone -d '{ "model": "clef-flash", "state": "The user took this screenshot.", | High | 9/29/2026 |
| v0.35.0 | ## Decision models Ollama now supports decision models through `/v1/systemone`, based on [TypeSafe’s Jev API](https://typesafe.ai). Decision models return choices, probabilities, and scores instead of text. Use them for tasks such as ticket triage, model routing, and content classification. Available models: - [**Nimble**](https://ollama.com/library/nimble) from Bespoke Labs - [**Tev1**](https://ollama.com/library/tev1) from Together AI ```sh ollama pull nimble ``` Send contex | High | 9/28/2026 |
| v0.40.0 | ## What's Changed **Models run on MLX on Apple Silicon by default** In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX. ``` ollama pull qwen3.8 ollama run qwen3.8 ``` Additional models include [gemma4](https://ollama.com/library/gemma4), [qwen3.6](https://ollama.com/library/qwen3.6) and [qwen3.5](https://ollama.com/library/qwen3.5) Decision models are now available on MLX as well: [Nimble](https://ollama.com | Medium | 9/25/2026 |
| v0.34.4 | ## What's Changed - Structured outputs on thinking models now apply in a single pass, making them faster and more reliable. - Fixed intermittent "model not found" errors with a large local library - Fixed the macOS app becoming unresponsive when checking if ChatGPT or Codex is running. - Qwen 3.8 prompt processing is faster on Apple Silicon. - Gemma 4 on Apple Silicon now picks the best image resolution per image, keeping more detail in high-resolution images. - Updated llama.cpp, MLX, a | High | 9/23/2026 |
| v0.34.3 | ## What's Changed `GET /api/show` now advertises each model's thinking controls and default: Available in the CLI with: ``` ollama show gemma4 ``` ``` thinking levels false, true default true ``` Available in the API with: ```sh curl http://localhost:11434/api/show -d '{"model": "glm-5.3-flash:cloud"}' ``` ```json { "thinking": { "values": ["low", "high", "max"], "default": "max" } } ``` Also available on ollama.com direc | High | 9/19/2026 |
| v0.34.2 | ## What's Changed - Added first-run setup when running `ollama`, with options to sign in or continue locally. Setup completion is shared with the desktop app on macOS and Windows. - Added `ollama://apps` to open the desktop app’s Apps page directly on macOS and Windows. - Fixed excessive memory growth during long generations with MLX speculative decoding. - Updated llama.cpp. **Full Changelog**: https://github.com/ollama/ollama/compare/v0.34.1...v0.34.2 | High | 9/15/2026 |
| v0.34.1 | ## What's Changed * MLX safetensors `ollama create` no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization. * Improved MLX memory handling on Apple Silicon * Runaway repeat token detection now requires 100 repeat tokens for reduced false positives (e.g. OCR) * `/api/tags` is much faster on large model libraries (3.1 s → 294 ms cold in testing), and model capabilities are now reported consistently. * Deprecated `typical_p` | High | 9/14/2026 |
| v0.34.0 | ## Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. <img width="1374" height="1300" alt="CleanShot 2026-09-08 at 11 04 07 AM@2x" src="https://github.com/user-attachments/assets/e10e299d-c11f-447d-9234-afa855824efe" /> This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible | High | 9/5/2026 |
| v0.33.2 | ## What's Changed * Ollama's app now follows the system appearance again, restoring dark mode support * Fixed the macOS app to properly hand off to an already-running instance instead of starting a second one * The Claude Desktop proxy no longer interrupts in-flight requests when the model catalog updates **Full Changelog**: https://github.com/ollama/ollama/compare/v0.33.1...v0.33.2 | High | 8/27/2026 |
| v0.32.14 | ## What's Changed * llm: transcode WebP images for llama-server * renderers/qwen: tolerate non-leading system messages **Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.13...v0.32.14 | High | 8/15/2026 |
| v0.32.6 | ## What's Changed - Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically - `/v1/chat/completions` streaming now matches OpenAI's wire format: `role` only on the first chunk, `finish_reason` on its own chunk, and usage in a separate chunk with `stream_options.include_usage`. - Truncated OpenAI responses now report `finish_reason: "length"` instead of `"tool_calls"`. - `ollama run kimi-k3` now offers `kimi-k3:cloud` for | High | 8/4/2026 |
| v0.32.3 | ## What's Changed - Fixed model downloads that stall before sending data. - Improved integrations: restored Claude Code Channels, fixed Anthropic thinking streams, and made Hermes Desktop respect `--force-build`. - Expanded GPU support with CUDA on Windows ARM64, B200 support through CUDA 12, and lower memory use on Linux CUDA/ROCm iGPUs. - Added chat, thinking, and tool calling support for Laguna 2.1 models, including a Metal inference fix. - Fixed GLM tool calls being silently dropped a | High | 7/23/2026 |
| v0.32.0 | ## What's Changed - New interactive agent experience: running `ollama` now launches an agent to help you code and delegate work ``` ❯ ollama Ollama 0.32.0 ▸ Chat, Code, & Work (glm-5.2:cloud) Chat with models, code, search the web, and delegate real work ``` - Renamed the Codex App integration to ChatGPT: use ollama launch chatgpt (and --restore to return to your usual ChatGPT profile) - Simplified integration selection: the ollama launch menu now only offers the most popu | High | 7/11/2026 |
| v0.31.1 | ## Faster Gemma 4 on Apple Silicon <img width="1037" height="485" alt="Screenshot 2026-06-30 at 5 25 29 PM" src="https://github.com/user-attachments/assets/547d5076-090f-43c4-a661-938e11abc955" /> Gemma 4 is now significantly faster in Ollama on Apple Silicon, generating tokens nearly 90% faster on average across a coding-agent benchmark by leveraging multi-token prediction (MTP). Ollama auto-tunes how many tokens to draft as it runs, so the speedup is on by default, requires no configurat | High | 6/30/2026 |
| v0.30.11 | ## What's Changed * launch: add thinking capability detection to opencode by @hoyyeva in https://github.com/ollama/ollama/pull/15434 * launch: auto-install Claude Code by @hoyyeva in https://github.com/ollama/ollama/pull/16802 * launch: auto-install opencode when missing by @hoyyeva in https://github.com/ollama/ollama/pull/16806 * discover: fix inverted iGPU/dGPU Vulkan classification on Windows hybrid graphics by @Sahil170595 in https://github.com/ollama/ollama/pull/16669 * mlxrunner: unif | High | 6/25/2026 |
| v0.30.10 | ## What's Changed * Command A and North family models now run on Apple Silicon with the MLX engine * Updated the underlying llama.cpp engine to build 9672 * Fixed build artifacts for MLX **Full Changelog**: https://github.com/ollama/ollama/compare/v0.30.9...v0.30.10 | High | 6/17/2026 |
| v0.30.8 | ## What's Changed * Fixed `ollama launch` selecting the wrong provider in some cases * Improved prompt caching by decoupling it from context shift for better KV cache reuse * More stable MLX inference with hardened linear and embedding layers * MLX runner now creates snapshots during prompt processing and speculative decoding for improved reliability * Improved recurrent model support with per-boundary states from the gated-delta kernels **Full Changelog**: https://github.com/ollama/olla | High | 6/12/2026 |
| v0.30.7 | Ollama Launch now supports Hermes Desktop, a native desktop interface for the Hermes agent. Run it alongside your Hermes agent to get a visual interface for managing conversations, integrations, and messaging apps. ``` ollama launch hermes-desktop ``` <img width="2556" height="1716" alt="image" src="https://github.com/user-attachments/assets/3b2292d8-9f94-4d32-9023-85772e6ab3f8" /> What's Changed - Hermes Desktop is now available via `ollama launch hermes-desktop` with native Windows | High | 6/7/2026 |
| v0.30.2 | ## What's Changed * feat(launch): show and auto-install Cline CLI by @hoyyeva in https://github.com/ollama/ollama/pull/16402 * log template details to aid troubleshooting by @dhiltgen in https://github.com/ollama/ollama/pull/16403 * cmd/launch: add Qwen code integration by @hoyyeva in https://github.com/ollama/ollama/pull/15900 * launch: fix opencode local model limits by @dhiltgen in https://github.com/ollama/ollama/pull/16425 * llm: include cached prompt tokens in llama-server counts by @ | High | 6/3/2026 |
| v0.24.0 | ## Codex App Ollama 0.24 includes support for the Codex App, OpenAI's desktop experience for working on Codex threads in parallel with built-in worktree support and git functionality. ```bash ollama launch codex-app ``` <img width="2088" height="1404" alt="CleanShot 2026-05-14 at 15 04 18@2x" src="https://github.com/user-attachments/assets/53bd7997-19fd-4809-b8f2-b6ed284369c9" /> ### Built-in browser Codex can load local servers and sites in its built-in browser, enabling you to | High | 5/14/2026 |
| v0.23.4 | ## What's Changed * `ollama launch opencode` now supports vision models with image inputs * Fixed formatting of Claude tool results when using local image paths **Full Changelog**: https://github.com/ollama/ollama/compare/v0.23.3...v0.23.4 | High | 5/13/2026 |
| v0.30.0 | Ollama 0.30 is now available, with improved compatibility and performance using [llama.cpp](https://github.com/ggml-org/llama.cpp). This augments the MLX engine on Apple Silicon, bringing support to a wider range of hardware. This release brings support for a wider range of models, including GGUF-based models from Hugging Face and your own fine-tuned models along with faster performance on NVIDIA hardware. ## Known issues: * `laguna-xs.2` is not yet supported on Windows/Linux. * `llama | Medium | 5/13/2026 |
| v0.23.2 | ## What's Changed * `ollama launch` no longer includes Claude Desktop due to the third-party integration being limited to Anthropic models. * Use `ollama launch claude-desktop --restore` to restore Claude Desktop to its normal state. * `/api/show` responses are now cached, improving median latency by **~6.7x** which will increase load speed for integrations like VS Code. * Improved backup workflow when managing launch integrations * Cleaner image generation layout in the MLX runner ** | High | 5/7/2026 |
| v0.23.0 | ## Claude Desktop Claude Desktop is now supported with Ollama Launch. Claude Cowork and Claude Code are supported within the Claude Desktop App. ``` ollama launch claude-desktop ``` ### Claude Cowork <img width="1272" height="872" alt="ca1" src="https://github.com/user-attachments/assets/1d550e3f-0272-4429-8cb2-06d32344cb77" /> ### Claude Code <img width="1272" height="872" alt="ca2" src="https://github.com/user-attachments/assets/f2a5ed5f-3069-4975-bb22-ada82914a01c" />
| High | 5/3/2026 |
| v0.22.0 | ## New models * NVIDIA's [Nemotron 3 Omni](https://ollama.com/library/nemotron3) * Poolside's first open-weight coding model - [Laguna XS.2](https://ollama.com/library/laguna-xs.2) **Full Changelog**: https://github.com/ollama/ollama/compare/v0.21.2...v0.22.0 | High | 4/28/2026 |
| v0.21.2 | ## What's Changed * Improved reliability of the OpenClaw onboarding flow in `ollama launch` * Recommended models in `ollama launch` now appear in a fixed, canonical order * OpenClaw integration now bundles Ollama's web search plugin in OpenClaw ## New Contributors * @madflow made their first contribution in https://github.com/ollama/ollama/pull/15733 **Full Changelog:** https://github.com/ollama/ollama/compare/v0.21.1...v0.21.2 | High | 4/23/2026 |
| v0.21.1 | ## What's Changed ### Kimi CLI You can now install and run the Kimi CLI through Ollama. ``` ollama launch kimi --model kimi-k2.6:cloud ``` Kimi CLI with Kimi K2.6 excels at long horizon agentic execution tasks through a multi-agent system. * **MLX runner adds logprobs support** for compatible models * **Faster MLX sampling** with fused top-P and top-K in a single sort pass, plus repeat penalties applied in the sampler * **Improved MLX prompt tokenization** by moving tokenizati | High | 4/22/2026 |
| v0.21.0 | ## Hermes Agent ``` ollama launch hermes ``` Hermes learns with you, automatically creating skills to better serve your workflows. Great for research and engineering tasks. <img width="1329" height="946" alt="image" src="https://github.com/user-attachments/assets/771d3383-95ed-4652-81e5-cf89514d25cc" /> ## What's Changed - **Gemma 4 on MLX.** Added support for running Gemma 4 via MLX on Apple Silicon, including a text-only MLX runtime for the model. The MLX backend also picked u | High | 4/16/2026 |
| v0.20.7 | ## What's Changed * Fix quality of gemma:e2b and gemma:e4b when thinking is disabled * ROCm: Update to ROCm 7.2.1 on Linux by @saman-amd in https://github.com/ollama/ollama/pull/15483 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.20.6...v0.20.7 | High | 4/13/2026 |
| v0.20.6 | ## What's Changed * Gemma 4 tool calling ability is improved and updated to use Google's latest post-launch fixes * Parallel tool calling improved for streaming responses * [Hermes agent](https://docs.ollama.com/integrations/hermes) Ollama integration guide is now available * Ollama app is updated to fix image attachment errors ## New Contributors @matteocelani made their first contribution in [#15272](https://github.com/ollama/ollama/pull/15272) **Full Changelog**: https://github | Medium | 4/12/2026 |
| v0.20.5 | ## OpenClaw channel setup with Ollama Launch <img width="2292" height="1694" alt="CleanShot 2026-04-09 at 15 45 10@2x" src="https://github.com/user-attachments/assets/3a6882c4-5c6e-4724-8f6e-56ff2df39f6f" /> ## What's Changed - OpenClaw channel setup: connect WhatsApp, Telegram, Discord, and other messaging channels through `ollama launch openclaw` - Enable flash attention for Gemma 4 on compatible GPUs - ollama launch openclaw now detects curl-based OpenCode installs at ~/.opencode | High | 4/9/2026 |
| v0.20.4 | ## What's Changed * mlx: Improve M5 performance with NAX * gemma4: enable flash attention **Full Changelog**: https://github.com/ollama/ollama/compare/v0.20.3...v0.20.4 | High | 4/7/2026 |
| v0.20.3 | ## What's Changed * Gemma 4 Tool Calling improvements * Added latest models to Ollama App * OpenClaw fixes for launching TUI **Full Changelog**: https://github.com/ollama/ollama/compare/v0.20.2...v0.20.3 | Medium | 4/7/2026 |
| v0.20.2 | ## What's Changed * app: default app home view to new chat instead of launch by @jmorganca in https://github.com/ollama/ollama/pull/15312 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.20.1...v0.20.2 | Medium | 4/4/2026 |
| v0.20.1 | ## What's Changed * bench: add prompt calibration, context size flag, and NumCtx reporting by @dhiltgen in https://github.com/ollama/ollama/pull/15158 * model/parsers: fix gemma4 arg parsing when quoted strings contain " by @drifkin in https://github.com/ollama/ollama/pull/15254 * ggml: skip cublasGemmBatchedEx during graph reservation by @jessegross in https://github.com/ollama/ollama/pull/15301 * gemma4: enable flash attention by @dhiltgen in https://github.com/ollama/ollama/pull/15296 * | Medium | 4/3/2026 |
| v0.20.0 | <img width="3748" height="1290" alt="Gemma 4" src="https://github.com/user-attachments/assets/c4727579-47b1-4c7b-8aa2-28eda15b71f5" /> ## Gemma 4 **Effective 2B (E2B)** ``` ollama run gemma4:e2b ``` **Effective 4B (E4B)** ``` ollama run gemma4:e4b ``` **26B (Mixture of Experts model with 4B active parameters)** ``` ollama run gemma4:26b ``` **31B (Dense)** ``` ollama run gemma4:31b ``` ## What's Changed * docs: update pi docs by @ParthSareen in https://github.com/ | Medium | 4/2/2026 |
| v0.19.0 | <img width="480" alt="image" src="https://github.com/user-attachments/assets/1b5ca980-b9d5-490e-99b9-f0f7b9af2c32" /> ## Ollama is now powered by MLX on Apple Silicon in preview Ollama on Apple silicon [is now built](https://ollama.com/blog/mlx) on top of Apple’s machine learning framework, MLX, to take advantage of its unified memory architecture. https://github.com/user-attachments/assets/600297b0-3167-46a5-8e3a-fefda3a51b84 Read more: https://ollama.com/blog/mlx ## What's Chang | Medium | 3/27/2026 |
| v0.18.4-rc0 | ## What's Changed * ggml: force flash attention off for grok by @rick-github in https://github.com/ollama/ollama/pull/15050 * mlx: fix KV cache snapshot memory leak by @jessegross in https://github.com/ollama/ollama/pull/15065 * mlxrunner: schedule periodic snapshots during prefill by @jessegross in https://github.com/ollama/ollama/pull/15058 * doc: update vscode doc by @hoyyeva in https://github.com/ollama/ollama/pull/15064 **Full Changelog**: https://github.com/ollama/ollama/compare/v0. | Medium | 3/26/2026 |
| v0.18.3 | ## Visual Studio Code Microsoft Visual Studio Code now directly integrates with Ollama via GitHub Copilot. If you have Ollama installed, any local or cloud model from Ollama can be selected for use within visual studio code. <img width="3410" height="2076" alt="Ollama screenshot 2026-03-26 at 01 43 57@2x" src="https://github.com/user-attachments/assets/4f9edc73-af3d-475c-924e-93334a4d88c5" /> ## What's Changed * GLM parser improvements for tool calls * OpenClaw integration improv | Medium | 3/25/2026 |
| v0.18.2 | ## What's Changed * Add extra check to ensure `npm` and `git` are installed before installing OpenClaw * Claude Code will now be faster when run locally, due to preventing cache breakages * Fix to correctly support `ollama launch openclaw --model <model>` * Register Ollama's websearch package correctly for OpenClaw **Full Changelog**: https://github.com/ollama/ollama/compare/v0.18.1...v0.18.2 | Low | 3/18/2026 |
| v0.18.1 | ### Web Search and Fetch in OpenClaw Ollama now ships with web search and web fetch plugin for OpenClaw. This allows Ollama's models (local or cloud) to search the web for the latest content and news. This also allows OpenClaw with Ollama to be able to fetch the web and extract readable content for processing. This feature does not execute JavaScript. When using local models with web search in OpenClaw, ensure you are signed into Ollama with `ollama signin` ``` ollama launch openclaw | Low | 3/17/2026 |
| v0.18.0 | Ollama 0.18 includes improved performance for OpenClaw and Ollama’s [cloud models](https://ollama.com/search?c=cloud), including the new Nemotron-3-Super model by NVIDIA designed for high-performance agentic reasoning tasks. ### Improved OpenClaw performance with Kimi-K2.5 This release of Ollama improves performance of cloud models and their reliability. - Up to 2x faster speeds with Kimi-K2.5 - Tool calling accuracy has been improved ``` ollama launch openclaw --model kimi-k2.5 ` | Low | 3/14/2026 |
| v0.17.8-rc4 | ## What's Changed * parsers: repair unclosed arg_value tags in GLM tool calls by @BruceMacD in https://github.com/ollama/ollama/pull/14656 * Reapply "don't require pulling stubs for cloud models" again by @jmorganca in https://github.com/ollama/ollama/pull/14608 * docs: format compat docs by @mxyng in https://github.com/ollama/ollama/pull/14678 * create: fix localhost handling by @dhiltgen in https://github.com/ollama/ollama/pull/14681 * build: smarter docker parallelism by @dhiltgen in htt | Low | 3/10/2026 |
| v0.17.7 | ## What's Changed * Allow thinking levels such as `"medium"` to correctly interpreted in Ollama's API for all thinking models * Add context length to support compaction when using `ollama launch` **Full Changelog**: https://github.com/ollama/ollama/compare/v0.17.6...v0.17.7 | Low | 3/5/2026 |
| v0.17.6 | ## What's Changed * Fixed issue where GLM-OCR would not work due to incorrect prompt rendering * Fixed tool calling parsing and rendering for Qwen 3.5 models ## New Contributors * @Victor-Quqi made their first contribution in https://github.com/ollama/ollama/pull/14584 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.17.5...v0.17.6 | Low | 3/4/2026 |
| v0.17.5 | ## New models - [Qwen3.5](https://ollama.com/library/qwen3.5): the small Qwen 3.5 model series is now available in 0.8B, 2B, 4B and 9B parameter sizes. ## What's Changed * Fixed crash in Qwen 3.5 models when split over GPU & CPU * Fixed issue where Qwen 3.5 models would repeat themselves due to no presence penalty (note: you may have to redownload the `qwen3.5` models: `ollama pull qwen3.5:35b` for example) * `ollama run --verbose` will now show peak memory usage when using Ollama's MLX | Low | 3/2/2026 |
| v0.17.4 | ## New models - [Qwen 3.5](https://ollama.com/library/qwen3.5): a family of open-source multimodal models that delivers exceptional utility and performance. - [LFM 2](https://ollama.com/library/lfm2): LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient. > Note: for users on 0.17.1, this version will not automatically update. [Re-downloading](h | Low | 2/27/2026 |
| v0.17.3 | ## What's Changed * Fixed issue where tool calls in the Qwen 3 and Qwen 3.5 model families would not be parsed correctly if emitted during thinking **Full Changelog**: https://github.com/ollama/ollama/compare/v0.17.2...v0.17.3 | Low | 2/27/2026 |
| v0.17.2 | ## What's Changed * Fixed issue where Ollama's app on Windows would crash when a new update has been downloaded **Full Changelog**: https://github.com/ollama/ollama/compare/v0.17.1...v0.17.2 | Low | 2/26/2026 |
| v0.17.1 | ## What's Changed * Nemotron architecture support in Ollama's engine * MLX engine now has improved memory usage * Ollama's app will now allow models that support tools to use web search capabilities * Improved LFM2 and LFM2.5 models in Ollama's engine * `ollama create` will no longer default to affine quantization for unquantized models when using the MLX engine * Added configuration for disabling automatic update downloading **Full Changelog**: https://github.com/ollama/ollama/compar | Low | 2/24/2026 |
| v0.17.0 | ## OpenClaw OpenClaw can now be installed and configured automatically via Ollama, making it the easiest way to get up and running with OpenClaw with open models like Kimi-K2.5, GLM-5, and Minimax-M2.5. ### Get started `ollama launch openclaw` <img width="2368" height="1830" alt="oc1" src="https://github.com/user-attachments/assets/cb9443d6-92cc-4c13-b26b-87e5f6c09b4e" /> ### Web search in OpenClaw When using cloud models, websearch is enabled - allowing OpenClaw to search the | Low | 2/21/2026 |
| v0.16.3 | ## What's Changed * New `ollama launch cline` added for the Cline CLI * `ollama launch <integration>` will now always show the model picker * Added Gemma 3, Llama and Qwen 3 architectures to MLX runner ## New Contributors * @hellosaumil made their first contribution in https://github.com/ollama/ollama/pull/14271 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.16.2...v0.16.3 | Low | 2/19/2026 |
| v0.16.2 | ## What's Changed * `ollama launch claude` now supports searching the web when using `:cloud` models * Fixed rendering issue when running `ollama` in PowerShell * New setting in Ollama's app makes it easier to disable cloud models for sensitive and private tasks where data cannot leave your computer. For Linux or when running `ollama serve` manually, set `OLLAMA_NO_CLOUD=1`. * Fixed issue where experimental image generation models would not run in 0.16.0 and 0.16.1 **Full Changelog**: h | Low | 2/14/2026 |
| v0.16.1 | ## What's Changed * Installing Ollama via the `curl` install script on macOS will now only prompt for your password if its required * Installing Ollama via the `iem` install script in Windows will now show progress * Image generation models will now respect the `OLLAMA_LOAD_TIMEOUT` variable **Full Changelog**: https://github.com/ollama/ollama/compare/v0.16.0...v0.16.1 | Low | 2/12/2026 |
| v0.16.0 | ## New models * [GLM-5](https://ollama.com/library/glm-5): A strong reasoning and agentic model from Z.ai with 744B total parameters (40B active), built for complex systems engineering and long-horizon tasks. * [MiniMax-M2.5](https://ollama.com/library/minimax-m2.5): a new state-of-the-art large language model designed for real-world productivity and coding tasks. ## New `ollama` The new `ollama` command makes it easy to launch your favorite apps with models using Ollama <img width="1 | Low | 2/12/2026 |
| v0.15.6 | ## What's Changed * Fixed context limits when running `ollama launch droid` * `ollama launch` will now download missing models instead of erroring * Fixed bug where `ollama launch claude` would cause context compaction when providing images **Full Changelog**: https://github.com/ollama/ollama/compare/v0.15.5...v0.15.6 | Low | 2/7/2026 |
| v0.15.5 | ## New models - [Qwen3-Coder-Next](https://ollama.com/library/qwen3-coder-next): a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development. - [GLM-OCR](https://ollama.com/library/glm-ocr): GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture. ## Improvements to `ollama launch` * `ollama launch` can now be provided arguments, for example `ollama launch claude -- --re | Low | 2/3/2026 |
| v0.15.4 | ## What's Changed * `ollama launch openclaw` will now enter the standard OpenClaw onboarding flow if this has not yet been completed. **Full Changelog**: https://github.com/ollama/ollama/compare/v0.15.3...v0.15.4 | Low | 2/1/2026 |
| v0.15.3 | ## What's Changed * Renamed `ollama launch clawdbot` to `ollama launch openclaw` to reflect the project's new name * Improved tool calling for Ministral models * docs: add clawdbot by @ParthSareen in https://github.com/ollama/ollama/pull/13925 * cmd/config: Use envconfig.Host() for base API in launch config packages by @gabe-l-hart in https://github.com/ollama/ollama/pull/13937 * `ollama launch` will now use the value of `OLLAMA_HOST` when running it ## New Contributors * @MBerguer made | Low | 2/1/2026 |
| v0.15.2 | <img width="1916" height="976" alt="Ollama screenshot 2026-01-26 at 17 53 40@2x (1)" src="https://github.com/user-attachments/assets/7937e607-e16e-46f5-a280-5cf9ce088a68" /> ## What's Changed * New `ollama launch clawdbot` command for launching Clawdbot using Ollama models **Full Changelog**: https://github.com/ollama/ollama/compare/v0.15.1...v0.15.2 | Low | 1/27/2026 |
| v0.15.1 | ## What's Changed * GLM-4.7-Flash performance and correctness improvements, fixing repetitive answers and tool calling quality * Fixed performance issues on macOS and arm64 Linux * Fixed issue where `ollama launch` would not detect `claude` and would incorrectly update `opencode` configurations ## New Contributors * @stillhart made their first contribution in https://github.com/ollama/ollama/pull/13855 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.15.0...v0.15.1 | Low | 1/24/2026 |
| v0.15.0 | <img width="4502" height="2222" alt="An image of Ollama building rapidly on the computer. Build with Ollama!" src="https://github.com/user-attachments/assets/0810fb5c-6727-400a-b711-4ffc349d0bb5" /> ## `ollama launch` A new `ollama launch` command to use Ollama's models with Claude Code, Codex, OpenCode, and Droid without separate configuration. ## What's Changed * New `ollama launch` command for Claude Code, Codex, OpenCode, and Droid * Fixed issue where creating multi-line strings | Low | 1/21/2026 |
| v0.14.3 | <img width="2904" height="1420" alt="Ollama screenshot 2026-01-20 at 23 41 54@2x" src="https://github.com/user-attachments/assets/ae16dbc5-5b2b-45fd-ae03-ba15f2721c3c" /> * [Z-Image Turbo](https://ollama.com/x/z-image-turbo): 6 billion parameter text-to-image model from Alibaba’s Tongyi Lab. It generates high-quality photorealistic images. * [Flux.2 Klein](https://ollama.com/x/flux2-klein): Black Forest Labs’ fastest image-generation models to date. ## New models * [GLM-4.7-Flash](https: | Low | 1/16/2026 |
| v0.14.2 | ## New models - [TranslateGemma](https://ollama.com/library/translategemma): A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages. ## What's Changed * <kbd>Shift</kbd> + <kbd>Enter</kbd> (or <kbd>Ctrl</kbd> + <kbd>j</kbd>) will now enter a newline in Ollama's CLI * Improve `/v1/responses` API to better confirm to OpenResponses specification ## New Contributors * @yuhongsun96 made their first contribution in https://github.com/ol | Low | 1/16/2026 |
| v0.14.1 | ## Image generation models (experimental) Experimental image generation models are available for **macOS** and **Linux (CUDA)** in Ollama: ### Available models - [Z-Image-Turbo](https://ollama.com/x/z-image-turbo) ``` ollama run x/z-image-turbo ``` > **Note**: [`x`](https://ollama.com/x) is a username on ollama.com where experimental models are uploaded More models coming soon: 1. Qwen-Image-2512 2. Qwen-Image-Edit-2511 3. GLM-Image ## What's Changed * fix macOS auto | Low | 1/14/2026 |
| v0.14.0 | ## What's Changed * `ollama run --experimental` CLI will now open a new Ollama CLI that includes an agent loop and the `bash` tool * Anthropic API compatibility: support for the `/v1/messages` API * A new `REQUIRES` command for the `Modelfile` allows declaring which version of Ollama is required for the model * For older models, Ollama will avoid an integer underflow on low VRAM systems during memory estimation * More accurate VRAM measurements for AMD iGPUs * Ollama's app will now highlig | Low | 1/10/2026 |
| v0.13.5 | ## New Models * Google's [FunctionGemma](https://ollama.com/library/functiongemma) a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling. ## What's Changed * `bert` architecture models now run on Ollama's engine * Added built-in renderer & tool parsing capabilities for DeepSeek-V3.1 * Fixed issue where nested properties in tools may not have been rendered properly ## New Contributors * @familom made their first contribution in https://github.c | Low | 12/18/2025 |
| v0.13.4 | ## New Models * [Nemotron 3 Nano](https://ollama.com/library/nemotron-3-nano): A new Standard for Efficient, Open, and Intelligent Agentic Models * [Olmo 3](https://ollama.com/library/olmo-3) and [Olmo 3.1](https://ollama.com/library/olmo-3.1): A series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets. ## What's Changed * Enable Flash Attention automatically for models by d | Low | 12/13/2025 |
| v0.13.3 | ## New models * [Devstral-Small-2](https://ollama.com/library/devstral-small-2): 24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents. * [rnj-1](https://ollama.com/library/rnj-1): Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models. * [nomic-embed-text-v2](https://ollama.com/library/nomic-embed-text- | Low | 12/9/2025 |
| v0.13.2 | ## New models - [Qwen3-Next](https://ollama.com/library/qwen3-next): The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed. ## What's Changed * Flash attention is now enabled by default for vision models such as `mistral-3`, `gemma3`, `qwen3-vl` and more. This improves memory utilization and performance when providing images as input. * Fixed GPU detection on multi-GPU CUDA machines * Fixed issue where `deepseek-v3 | Low | 12/4/2025 |
| v0.13.1 | ## New models - [Ministral-3](https://ollama.com/library/ministral-3): The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. - [Mistral-Large-3](https://ollama.com/library/mistral-large-3): A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads. ## What's Changed * `nomic-embed-text` will now use Ollama's engine by default * Tool calling support for `cogito-v2.1` * Fixed issues with CUDA | Low | 11/27/2025 |
| v0.13.0 | ## New models * [DeepSeek-OCR](https://ollama.com/library/deepseek-ocr): DeepSeek-OCR uses optical 2D mapping to compress long contexts, achieving high OCR precision with reduced vision tokens and demonstrating practical value in document processing. * [Cogito-V2.1](https://ollama.com/library/cogito-2.1): instruction tuned generative models, currently the best open-weight LLM by a US company ## DeepSeek-OCR DeepSeek-OCR is now available on Ollama. Example inputs: ``` ollama run deeps | Low | 11/19/2025 |
| v0.12.11 | ## Logprobs Ollama's API and OpenAI-compatible API now support [log probabilities](https://cookbook.openai.com/examples/using_logprobs). Log probabilities of output tokens indicate the likelihood of each token occurring in the sequence given the context. This is useful for different use cases: 1. Classification tasks 2. Retrieval (Q&A) evaluation 3. Autocomplete 4. Token highlighting and outputting bytes 5. Calculating perplexity To enable Logprobs, provide `"logprobs": true` to Ol | Low | 11/12/2025 |
| v0.12.10 | ## `ollama run` now works with embedding models `ollama run` can now run embedding models to generate vector embeddings from text: ``` ollama run embeddinggemma "Hello world" ``` Content can also be provided to `ollama run` via standard input: ``` echo "Hello world" | ollama run embeddinggemma ``` ## What's Changed * Fixed errors when running `qwen3-vl:235b` and `qwen3-vl:235b-instruct` * Enable flash attention for Vulkan (currently needs to be built from source) * Add Vulk | Low | 11/5/2025 |
| v0.12.9 | ## What's Changed * Fix performance regression on CPU-only systems **Full Changelog**: https://github.com/ollama/ollama/compare/v0.12.8...v0.12.9 | Low | 10/31/2025 |
| v0.12.8 | <img width="512" height="512" alt="Ollama_halloween_background" src="https://github.com/user-attachments/assets/ac1f37c5-c81a-446f-8e99-97ef5ebd7d05" /> ## What's Changed * `qwen3-vl` performance improvements, including flash attention support by default * `qwen3-vl` will now output less leading whitespace in the response when thinking * Fixed issue where `deepseek-v3.1` thinking could not be disabled in Ollama's new app * Fixed issue where `qwen3-vl` would fail to interpret images with | Low | 10/30/2025 |
| v0.12.7 | <img width="600" alt="Ollama screenshot 2025-10-29 at 13 56 55@2x" src="https://github.com/user-attachments/assets/4fea0b30-5d31-4da2-b99c-7f38606fc0a2" /> ## New models - [Qwen3-VL](https://ollama.com/library/qwen3-vl): Qwen3-VL is now available in all parameter sizes ranging from 2B to 235B - [MiniMax-M2](https://ollama.com/library/minimax-m2): a 230 Billion parameter model built for coding & agentic workflows available on Ollama's cloud ## Add files and adjust thinking levels in Oll | Low | 10/29/2025 |
