# Ollama v0.19.0 — Release & Upgrade Intelligence
- **Product:** Ollama (https://ollama.com)
- **Version:** v0.19.0
- **Released:** Mar 27, 2026
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/ollama/updates/v0.19.0/

## Executive Summary (TL;DR)
Ollama v0.19.0. Source highlight: <img width="480" alt="image" src="https://github.com/user-attachments/assets/1b5ca980-b9d5-490e-99b9-f0f7b9af2c32" />

## Improvements
- Improved KV cache hit rate when using the Anthropic-compatible API

## Bug Fixes
- Fixed tool call parsing issue with Qwen3.5 where tool calls would be output in thinking
- Fixed KV cache snapshot memory leak in MLX runner
- Fixed issue where flash attention would be incorrectly enabled for `grok` models
- Fixed `qwen3-next:80b` not loading in Ollama