Ollama

What's Changed Support for Cohere2Moe architecture Fixed LFM2 parser/render for cases where thinking was not emitted Fixed issue where `ollama launch claude` and other coding agent or assistant use ca…

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 har…

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 m…

New models - Gemma 4 QAT weights: the Gemma 4 family is now optimized with Quantization-Aware Training (QAT) to dramatically reduce memory requirements and maximize on-device performance. Look for the…

What's Changed Fixed the `gemma4:12b` floating point exception crash on x86, CUDA, Linux, and Windows systems. `ollama launch hermes-desktop` now launches Hermes Desktop and can skip rebuilding when a…

New models - Nemotron-3-Ultra: NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows. What's Changed * Fixed multimodal models not using GPU on the llama.cpp…

New models - Gemma 4 12B: high-performance multimodal intelligence that runs directly on laptops, combining efficiency with advanced reasoning. What's Changed * Added support for `gemma4:12b`. Full Ch…

What's Changed `ollama launch` now supports Qwen Code and can guide users through installing the Cline CLI when it is missing. `ollama launch codex` now uses an isolated launch configuration, avoiding…

What's Changed feat(launch): show and auto-install Cline CLI by @hoyyeva in log template details to aid troubleshooting by @dhiltgen in * cmd/launch: add Qwen code integration by @hoyyeva in

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 laun…

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:

Ollama 0.30 is now available, with improved compatibility and performance using llama.cpp. This augments the MLX engine on Apple Silicon, bringing support to a wider range of hardware. This release br…

What's Changed mlx: refined model push behavior by @dhiltgen in test: integration test hardening by @dhiltgen in app: harden update flows by @dhiltgen in

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 De…

Gemma 4 MTP (Multi-token Processing) for the MLX runner Gemma 4 MTP speculative decoding is now supported on Macs. This can give over a 2x speed increase for the Gemma 4 31B model on coding tasks. ```…

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 wi…

What's Changed Updated the Gemma 4 renderer for thinking and tool calling improvements Model recommendations are now updated without updating Ollama Aligned the desktop app's launch page with `ollama…

New models NVIDIA's Nemotron 3 Omni Poolside's first open-weight coding model - Laguna XS.2 Full Changelog:

What's Changed api: accept "max" as a think value by @ParthSareen in openai: map responses reasoning effort to think by @ParthSareen in Full Changelog:

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 Oll…

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 tas…

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"…

What's Changed ROCm: Update to ROCm 7.2.1 on Linux by @saman-amd in gemma4: fix nothink case renderer by @drifkin in * gemma4: fix compiler error on metal by @dhiltgen in

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 Full Changelog:

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 Ollama integration guid…

OpenClaw channel setup with `ollama launch` What's Changed - OpenClaw channel setup: connect WhatsApp, Telegram, Discord, and other messaging channels thro

What's Changed mlx: Improve M5 performance with NAX gemma4: enable flash attention Full Changelog:

What's Changed Gemma 4 Tool Calling improvements Added latest models to Ollama App * OpenClaw fixes for launching TUI Full Changelog:

What's Changed * app: default app home view to new chat instead of launch by @jmorganca in Full Changelog:

What's Changed bench: add prompt calibration, context size flag, and NumCtx reporting by @dhiltgen in model/parsers: fix gemma4 arg parsing when quoted strings contain " by @drifkin in * ggml: skip cu…

Gemma 4 Effective 2B (E2B) ``` ollama run gemma4:e2b ``` Effective 4B (E4B) ``` ollama run gemma4:e4b ``` **26B (Mixture of Experts mod

Ollama is now powered by MLX on Apple Silicon in preview Ollama on Apple silicon is now built on top of Apple’s machine learning framework, ML

What's Changed ggml: force flash attention off for grok by @rick-github in mlx: fix KV cache snapshot memory leak by @jessegross in * mlxrunner: schedule periodic snapshots during prefill by @jessegro…

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 withi…

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 su…

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. Thi…

Ollama 0.18 includes improved performance for OpenClaw and Ollama’s cloud models, including the new Nemotron-3-Super model by NVIDIA designed for high-performance agentic reasoning tasks. Improved Ope…

What's Changed parsers: repair unclosed arg_value tags in GLM tool calls by @BruceMacD in Reapply "don't require pulling stubs for cloud models" again by @jmorganca in * docs: format compat docs by @m…

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 Change…

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…

New models - 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…

New models - Qwen 3.5: a family of open-source multimodal models that delivers exceptional utility and performance. - LFM 2: LFM2 is a family of hybrid models designed for on-device deployment. LFM2-2…

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:

What's Changed * Fixed issue where Ollama's app on Windows would crash when a new update has been downloaded Full Changelog:

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 L…

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.…

What's Changed New `ollama launch cline` added for the Cline CLI `ollama launch ` will now always show the model picker Added Gemma 3, Llama and Qwen 3 architectures to MLX runner New Contributors @he…

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…

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 p…

New models 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: a new state-of-the…

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…

New models - Qwen3-Coder-Next: a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development. - GLM-OCR: GLM-OCR is a multimodal OCR model for…

What's Changed * `ollama launch openclaw` will now enter the standard OpenClaw onboarding flow if this has not yet been completed. Full Changelog:

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 cmd/confi…

What's Changed New `ollama launch clawdbot` command for launching Clawdbot using Ollama models *Full Changelo

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…

`ollama launch` A new `ollama launch` command to use Ollama's models with Claude Code, Codex