Rapid-MLX

Local OpenAI- and Anthropic-compatible inference for Apple Silicon.

Run it on your Mac

curl -fsSL https://rapidmlx.com/install.sh | bash
rapid-mlx serve ling-3.0-tiny-4bit
curl -s http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{"model":"default","messages":[{"role":"user","content":"Say hello"}]}'

The example needs at least 8 GB unified memory; allow more for long contexts.

Use it from OpenCode / Claude Code / Codex: rapid-mlx agents <name> --setup · Agent setup