# Ollama v0.32.1 — Release & Upgrade Intelligence
- **Product:** Ollama (https://ollama.com)
- **Version:** v0.32.1
- **Released:** Jul 16, 2026
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/ollama/updates/v0.32.1/

## Executive Summary (TL;DR)
Ollama v0.32.1. Source highlight: Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations

## Improvements
- Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations

## Bug Fixes
- Fixed a recurrent MLX model cache leak that could increase memory use across requests, and improved cache snapshot performance
- Fixed `ollama launch` so choosing **Pick another model** for a deprecated model passed with `--model` opens the model picker