v0.33.1
Added 2
- Add Qwen3.8 Flash Next support for MLX
- Add structured output support to mlxrunner
Changed 2
- Make external compat patches idempotent in cmake
- Update MLX and llama.cpp
Fixed 1
- Avoid Metal GPU timeouts when loading models from slow storage in mlxrunner
From Ollama
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