Ollama v0.40.0 Enables Default MLX Runtime for Models on Apple Silicon

Core summary

One sentence to understand this update

Ollama v0.40.0-rc0 now automatically runs supported model architectures on MLX by default for Apple Silicon devices, enhancing performance.

Impact & opportunity

What this could mean

Apple Silicon users can expect improved performance and efficiency for local model inference with Ollama due to native MLX integration, simplifying setup.