ollama cache-optimization agent-reliability gemma4 memory-leak

Ollama fixes cache leak, improves tool calling

v0.32.1-rc0 patches MLX model cache memory leak, stabilizes Gemma 4 tool-response continuations, and adds working directory context to agents.

Summary

Memory leak fixes directly reduce production resource costs for long-running agent deployments. Improved tool calling reliability cuts failures in multi-turn reasoning workflows.

Why it matters

Memory leak fixes directly reduce production resource costs for long-running agent deployments. Improved tool calling reliability cuts failures in multi-turn reasoning workflows.

Implementation verdict

Drop-in patch for v0.32.0 users. Cache leak fix requires upgrade if you run persistent agents. Tool calling improvements benefit Gemma 4 users immediately; others see no breaking changes. Worth upgrading now if you've seen memory creep in multi-request sessions.

Sources

1.Fixed a recurrent MLX model cache leak that could increase memory use across requests
2.Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations
3.The interactive agent now receives the current working directory for better project context

Dev Signal

Get briefs like this in your inbox — free, every weekday.

100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.

Read the full issue →All briefs