BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

Ollama makes MLX default on Apple Silicon

Oct 6, 2026, first seen via Training & inference tooling releases

Ollama v0.40.0 made MLX the default runtime for supported Apple Silicon models and expanded MLX model support.

Read the original at github.comOpens the publisher's site in a new tab

More in Open-weight & owned stack

Mistral Releases Large 4 Open-Weight ModelOct 6Google Releases EmbeddingGemma 2 For On-Device SearchOct 6Reflection AI Launches Beam Open-Weight ModelOct 6Impersonating Hugging Face repository delivers infostealerOct 8Cantina releases open apex-flash-1 security modelOct 5