Ollama pre-release runs models on MLX by default on Apple Silicon

Ollama

Tools official 1 src. ~1 min

Ollama v0.40.0-rc0 makes MLX the default runtime on Apple Silicon for supported model architectures, replacing the llama.cpp path on Macs during the pre-release cycle.

Why it matters

Default MLX routing materially changes local inference performance on Macs, which dominate the Ollama user base.

Importance: 3/5

Default inference-engine switch for the dominant local-LLM tool on Mac

ollama mlx local-inference apple

Sources

official Ollama v0.40.0-rc0 release notes