Rapid-MLX
Local OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon built on MLX for coding agents.
Not verified yet
How far pickfit got
pickfit hasn’t verified Rapid-MLX yet, so there are no tested install steps.
What follows comes from its README only.
Use it
You need first
- Runtimes:
python,mlx - System packages:
ffmpeg - A GPU is required
- Apple silicon only
What it does
pickfit hasn’t run it yet, so these come from the README only.
- Reliable tool calling for coding agents with 27 parser modulesNot tested
- Continuous batching with radix prefix cache and quantized KV cacheNot tested
- Local image and video generation via OpenAI-compatible APIsNot tested
- Audio speech, transcription, voice cloning and music generationNot tested
Good for
- Serve local LLMs via OpenAI- and Anthropic-compatible API
- Run coding agents locally with a local model on Mac
- Chat with a model in the terminal REPL
- Generate images and video locally via OpenAI-compatible API
An alternative to oMLX, LM Studio, Ollama and mlx-lm.