Thursday, July 16, 2026Scoutari
Log inSign up
Sign up
ModelsSkill RadarSavedPersonalizeSubmit sourceLog in
Back to timeline

Thu, July 1613:53ToolsModel releasesOpen sourceAgentsModel releases guide

Ollama v0.32.1 Released: Gemma 4 Tool Calling, MLX Cache Fix

View originalGet it on GitHub

Decision Brief

What changedOllama v0.32.1 improves Gemma 4's tool calling and multi-turn reasoning, fixes MLX model cache leaks, and enhances Agent search and authentication flows.
Why it mattersThe MLX cache leak fix reduces long-running memory usage, crucial for MLX backend users.
Who should careAI coding tool users, Inference / infra teams
Affected stackOllama
Builder actionUpgrade Ollama to v0.32.1
Source confidenceHigh · Official release / blog / repo

Ollama v0.32.1 enhances Gemma 4's tool calling and multi-turn reasoning for more reliable tool response continuity. It fixes a duplicate cache leak in MLX models that could increase cross-request memory usage, and improves cache snapshot performance. MLX text model loading now respects the OLLAMA_LOAD_TIMEOUT variable. Agent web search and fetch will prompt users to run 'ollama signin' when authentication is required. Interactive agents now receive the current working directory for better project context. Fixes an issue in 'ollama launch' where selecting 'Pick another model' for deprecated models failed to open the model picker. Additionally, VS Code setup documentation for the official Ollama extension has been updated.

Summary basis: official / RSS sourceCompiled from the source scope noted above; the original remains authoritative.

Sources

Related intel

留言

登入后即可留言，和其他 builder 交换实测心得。

还没有留言，抢头香。