Ollama v0.40.0-rc0: MLX Runtime for Apple Silicon Models by Default

Core summary

One sentence to understand this update

Ollama v0.40.0-rc0 now defaults to running supported model architectures on MLX for Apple Silicon devices, significantly enhancing performance.

Impact & opportunity

What this could mean

Apple Silicon users can expect significantly faster local model inference, opening doors for more complex on-device AI applications.