Ollama releases· github-actions[bot]·· 12 days ago65
v0.40.14
v0.40.14
Brief overview
Ollama v0.40.14 released, Claude Code model output is no longer limited by the default 128k, cloud models can break this limit; fixed the decoding issue of compressed search responses for the /api/chat endpoint.
Article
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
Source: Ollama releases · github.com