§ local-llm · storyline
Automatically runs models on MLX on Apple Silicon
Ollama updates to automatically run supported models on MLX for Apple Silicon.
What's Changed Models run on MLX on Apple Silicon by default In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX. ``` ollama pull qwen3.8 ollama run qwen3.8 ``` During the pre-release we will be testing and enabling additional models.
Full Changelog: https://github.com/ollama/ollama/compare/v0.34.4...v0.40.0-rc0
§ sources1 publication · timeline below
- github.comOllama v0.40.0-rc2primary