archive
· today in ai · 2026-07-16
Ollama pre-release improves Gemma 4 tools
Archive item — written before sources were shown.
Ollama v0.32.1, a pre-release, improves Gemma 4 tool-calling reliability and fixes a recurring MLX model cache memory leak.
Tagged July 16 as a pre-release, v0.32.1 improves Gemma 4 tool-response continuations, fixes a recurring MLX model cache memory leak, speeds up cache-snapshot performance, gives the interactive agent working-directory context, and adds sign-in prompts for web-search features.
sources
- 01Ollama v0.32.1 release notes (pre-release)github.com/ollama · primary (release notes)
Rami Steitieh