Cheng(@zcbenz ):We have been expecting this since ollama's first pull request to MLX. It is just the beginning, CUDA & CPU backends are still improving and hopefully we will have one framework unifying inference & training for all platforms.

Cheng

@zcbenz

maintainer of MLX @apple. creator of @electronjs. check for the open source things I built.

Joined June 2007

97 Following 6.5K Followers

Cheng@zcbenz

2026.03.31 07:11

We have been expecting this since ollama's first pull request to MLX. It is just the beginning, CUDA & CPU backends are still improving and hopefully we will have one framework unifying inference & training for all platforms.

ollama@ollama

2026.03.31 04:27

Ollama is now updated to run the fastest on Apple silicon, powered by MLX, Apple's machine learning framework. This change unlocks much faster performance to accelerate demanding work on macOS: - Personal assistants like OpenClaw - Coding agents like Claude Code, OpenCode, or Codex