AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

ollama/ollama: v0.33.1

GitHub AI software releases · article · Aug 26, 2026 · UTC

## What's Changed * MLX: Qwen3.8 Flash Next support * cmake: make external compat patches idempotent * MLX and llama.cpp update * mlxrunner: add structured output support * mlxrunner: avoid Metal GPU timeouts when loading models from slow storage ## New Contributors * @pd95 made their first contribution in https://github.com/ollama/ollama/pull/17948 **Full Changelog**: https://github.com/ollama/ollama/compare/v0.33.0...v0.33.1

Read original source ↗ Open in workspace

recordType
software-release
evidenceStatus
publisher-reported
region
Global

Evidence & attribution

First collected: 2026-09-20T23:22:28.549Z. This is not the publication date.