Ollama - Package Updates
-
[1.18.0]
- Update ollama to 0.35.0
- Full Changelog
- Ollama now supports decision models through
/v1/systemone, based on TypeSafe's Jev API. - Decision models return choices, probabilities, and scores instead of text. Use them for tasks such as ticket triage, model routing, and content classification.
- Nimble from Bespoke Labs
- Tev1 from Together AI
- Settings now opens without waiting for model discovery.
- Fixed the macOS update menu and icon not reflecting an available update at startup.
- Fixed stalled MLX model downloads hanging indefinitely.
- Requests containing the deprecated
typical_pparameter now log a warning instead of failing.
-
[1.18.1]
- Update ollama to 0.35.1
- Full Changelog
- Models using web search can now perform up to ten searches per response, up from three
- Modelfiles now support
CAPABILITYdeclarations, so model creators can explicitly declare what a model can do. Declarations are preserved when creating from GGUF or safetensors, through model inheritance, and on Modelfile export ollama showand the model list now report onlydecisionas the capability for decision models, so clients no longer offer them for general chat, tools, or thinking- Updated llama.cpp and the MLX engine
-
[1.19.0]
- Update ollama to 0.40.0
- Full Changelog
- 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.
- Additional models include gemma4, qwen3.6 and qwen3.5
- Decision models are now available on MLX as well: Nimble tev1 clef clef-flash
- MLX now has support for an embedding model: embeddinggemma-2
- We will continue testing and enabling additional models.
- Full Changelog: https://github.com/ollama/ollama/compare/v0.35.1...v0.40.0
-
[1.19.1]
- Update ollama to 0.40.1
- Full Changelog
- server: proxy cloud usage and balance APIs by @drifkin in #18829
- llama: fix clef head reads past 2GiB on windows by @Gigrise in #18777
- cmd: remove account step from CLI onboarding by @hoyyeva in #18826
- manifest: avoid symlinks on Windows by @dhiltgen in #18852
- docs: fix 6 dead links in README community integrations list by @aniketkrs in #18814
- docs: fix broken download links in app README by @chenlichao in #18233
- mlx: drop carried metal residency patch now that it is upstream by @dhiltgen in #18854
-
[1.19.2]
- Update ollama to 0.40.2
- Full Changelog
ollama listno longer shows duplicate entries for upgraded models by @dhiltgen in #18874ollama launch claudeuses the model's full context length by @jberg5 in #18855- README: add oxi to community integrations by @maziluiosif in #18739
-
[1.19.3]
- Update ollama to 0.40.3
- Full Changelog
ollama launch claudeno longer shows a warning about Claude connectors by @hoyyeva in #18878ollama launch codexno longer warns about service tiers by @hoyyeva in #18879- Paused background model upgrade for embedding and other request performance, by @jmorganca in #18908
-
[1.19.4]
- Update ollama to 0.40.4
- Full Changelog
- Kev decision models are now supported by the MLX runner on Apple silicon
ollama launchcan now be used with usage credits without upgrading to a paid planollama launch codexnow includes locally installed Ollama models in its model picker. Use/modelwithin the Codex CLI to swap models.- Improved inference performance by reusing verified manifests and already loaded models
- Added support for multimodal embeddings through llama-server
- Fixed loading multimodal embedding models with small context windows
- Improved Gemma 4 prefill performance on NVIDIA GPUs with the MLX runner
- MLX runner now clips long Laya states instead of rejecting them
- Improved speculative decoding reliability in the MLX runner, including recurrent state handling after rollback
- Updated llama.cpp with native decision model support
-
[1.19.5]
- Update ollama to 0.40.5
- Full Changelog
- Decision models are now available on cloud use
clef:cloudandclef-flash:cloudto run decision models through ollama.com cloud without pulling them locally - Continuing an OpenAI-compatible Responses conversation that includes custom tool calls no longer fails with an error
- Clearer error messages when cloud access fails: sign-in problems, payment issues in the desktop app, and upstream access errors from the ChatGPT gateway now explain what went wrong
- Updated llama.cpp (adding Nemotron 3.5 support) and MLX
- @willietran made their first contribution in #18986
- Full Changelog: https://github.com/ollama/ollama/compare/v0.40.4...v0.40.5
-
[1.19.6]
- Update ollama to 0.40.6
- Full Changelog
- win: prevent orphaned runners by @dhiltgen in #18500
- gguf: add the q2_0 tensor and file types by @jmorganca in #18967
- Launch clef in Ollama's cloud by @jberg5 in #19036
- use identifiers for --ask mode question keys by @jberg5 in #19041
- Full Changelog: https://github.com/ollama/ollama/compare/v0.40.5...v0.40.6-rc0
-
[1.19.7]
- Update ollama to 0.40.8
- Full Changelog
- pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B
- Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without thinking, or when the history contains another provider's compaction items
- Fixed streaming Responses requests where client tool calls (e.g. Codex with web search) could emit before open reasoning items, producing misordered/duplicate tool call events
- Requests routed to remote models are now cancelled on ollama.com when the client disconnects, instead of continuing to run
ollama shownow reports which renderer and parser a model uses and where its chat template comes from; the API exposes the same values in newrenderer,parser, andtemplate_sourcefields- More draft models now work with speculative decoding: llama-server infers the draft type automatically instead of requiring Ollama to identify it
ollama launch claudenow clampsCLAUDE_CODE_AUTO_COMPACT_WINDOWto Claude Code's supported range, avoiding a "window too large" warning- Updated llama.cpp and MLX
-
[1.19.8]
- Update ollama to 0.40.9
- Full Changelog
- Ollama can now generate speech with Phonon on Apple Silicon.
ollama runplays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through the OpenAI-compatible/v1/audio/speechendpoint. - d3 brings vLLM Semantic Router's decision models to Ollama. Give a model text, structured state, or an image, and ask it to classify, answer yes or no, or score options with probabilities. The family includes 2B, 4B, 9B, and 27B sizes.
- Flint now runs on Linux and Windows as well as macOS.
- Streaming OpenAI Responses and Anthropic Messages requests now report generation failures instead of ending silently after partial output.
ollama launchnow passes cloud models' context lengths and capabilities to coding tools, fixing incorrect context and compaction settings.- Anthropic-compatible web search now uses the model's supported thinking setting in follow-up requests, preventing avoidable failures.
-
[1.19.9]
- Update ollama to 0.40.10
- Full Changelog
- Nemotron 3.5 Bolt E4B 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.
- Full Changelog: https://github.com/ollama/ollama/compare/v0.40.9...v0.40.10
-
[1.19.10]
- Update ollama to 0.40.11
- Full Changelog
- Ollama can now generate speech on macOS.
ollama runplays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through the OpenAI-compatible/v1/audio/speechendpoint. - d3 brings vLLM Semantic Router's decision models to Ollama. Give a model text, structured state, or an image, and ask it to classify, answer yes or no, or score options with probabilities. The family includes 2B, 4B, 9B, and 27B sizes.
-
[1.19.11]
- Update ollama to 0.40.12
- Full Changelog
- Faster prompt processing on Apple silicon for Gemma 4, Flint and Laguna models
- Speculative decoding now supports DFlash2 draft models on MLX
- Gemma 4 keeps more detail in small images
ollama launchnow works with OpenCode v2- Fixed tool-only assistant turns from Kimi CLI
- Updated MLX and llama.cpp
Hello! It looks like you're interested in this conversation, but you don't have an account yet.
Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.
With your input, this post could be even better 💗
Register Login