Repository navigation
Releases
v0.40.17
What's Changed
- Improve ChatGPT CLI restore and graceful restart by @hoyyeva in #19583
- cmd/launch: use thinking metadata for OpenCode settings by @hoyyeva in #19409
- llm: use mmap for Vulkan integrated GPUs by @dhiltgen in #19640
- rpreslar4765/Ollama by @rpreslar4765 in #17163
- mlx: support concurrent generation by @dhiltgen in #19197
- llama.cpp: version bump b12257 by @dhiltgen in #19646
- MLX, MLX-C: version bump by @dhiltgen in #19647
New Contributors
- @rpreslar4765 made their first contribution in #17163
Full Changelog: v0.40.16...v0.40.17-rc0
v0.40.16
Ripple Preview
Ripple Preview from Ricursive Intelligence is a 65B dense model built for agentic coding.
ollama run ripple-previewWhat's Changed
- Qwen3.8 Flash Next uses about 27 GiB less memory on Apple silicon
ollama launch claudealways routes Claude Code to the selected modelollama launchexplains when a cloud model has been retired/v1/responsesrespectstruncationand no longer silently truncates by default/v1/modelsreturns an empty list instead ofnullwhen no models are installed- CUDA 13.5 support for Windows on ARM
- Updated llama.cpp
Full Changelog: v0.40.15...v0.40.16
v0.40.15
MiMo V2.6
Xiaomi MiMo's mimo-v2.6, a 9B model built for code and agent workflows, is now supported in Ollama.
ollama run mimo-v2.6AutoTrust decision models
AutoTrust decision models read text and return choices, yes or no probabilities, and ratings for the questions you supply. The family includes 9b, 35b, and 27b-vl sizes — the 35b and 27b-vl sizes can also read images.
ollama run autotrust-jev "A customer says their card was charged twice." --ask "Is this a billing issue?"Note: autotrust-jev is supported on Apple silicon in this release.
What's Changed
- ollama launch now supports Kimi Code CLI — the successor to kimi-cli — and offers to migrate existing kimi-cli setups
- ollama launch now fills in Pi's model list automatically so models can be picked inside Pi, and Claude Desktop's model
picker shows Ollama's actual model names - Recurrent and vision GGUF models can now serve more than one request at a time
- Qwen3 and Qwen3.5 models using long-context (YaRN) scaling
- Running ollama with no arguments opens the welcome launcher
Full Changelog: v0.40.14...v0.40.15
v0.40.14
What's Changed
ollama launch claudenow applies the model's output token limit for Claude Code, so cloud models no longer run into the 128k default cap- Cloud web search responses on
/api/chatare now decoded correctly, including compressed responses - OpenAI-compatible endpoints no longer override a model's packaged sampler defaults — clients that send no
temperature/top_pget the model's own values instead of 1.0, matching/api/chat /v1/responsesnow preserves readable input content, including prior assistant refusals, instead of flattening it- Ollama's app can now retry ChatGPT disconnect failures instead of leaving the connection in a broken state
ollama launch codexverifies ChatGPT routing before configuring, and reports a clear error when routing is unavailable- Faster top-k sampling on MLX for large vocabularies
Full Changelog: v0.40.13...v0.40.14
v0.40.13
LFM3 on Linux and Windows
Liquid AI's LFM3 models, including text-to-speech in lfm3-audio and lfm3-omni, now run on Linux and Windows as well as Apple silicon.
Full Changelog: v0.40.12...v0.40.13
v0.40.12
Liquid AI LFM3
LFM3 is Liquid AI's new family of small models built for local agents, tool calling, and structured output, on Liquid's new tri-hybrid architecture. The family includes:
- lfm3: a 1.7B text model with a 256K-token context window
- lfm3-vl: adds image understanding
- lfm3-audio: speech recognition, translation, and text-to-speech in 18 languages
- lfm3-omni: text, images, and audio in one model
ollama run lfm3d1 decision models
Liquid AI's d1 models now come in a 2B size, built on LFM3. d1 makes decisions about text and images, and d1-omni adds audio.
ollama run d1:2b "I was charged twice for order 4417." --ask "Is this a billing issue?"Note: lfm3 and d1 2b are supported on Apple hardware in this release. Support for Linux/Windows coming soon.
What's Changed
- 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
Full Changelog: v0.40.11...v0.40.12
v0.40.11
Speech
Ollama can now generate 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.
ollama run phonon "Hello from Ollama."d3 decision models
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.
ollama run d3 "A customer says their card was charged twice." --ask "Is this a billing issue?"New Contributors
- @SynapShift made their first contribution in #19173
Full Changelog: v0.40.10...v0.40.11
v0.40.10
NVIDIA Nemotron 3.5 Bolt E4B
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.
ollama run nemotron-3.5-bolt:e4b
Full Changelog: v0.40.9...v0.40.10
v0.40.9
Flint on Linux and Windows
Flint now runs on Linux and Windows as well as macOS.
Other improvements
- 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.
Full Changelog: v0.40.8...v0.40.9
v0.40.8
Recursive Flint
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 files and tool interactions.
Flint is an Apache 2.0-licensed, 40B-parameter mixture-of-experts model with approximately 2.5B parameters active per token. In its release evaluations, Recursive reports 54.9% on Terminal-Bench 2.1 and 74.2% on SWE-bench Verified.
ollama run flintNote: Flint is supported on MacOS. Other GPU support will be enabled in a subsequent release.
Full Changelog: v0.40.7...v0.40.8
