# Rapid-MLX

> Open-source LLM inference server compatible with OpenAI and Anthropic APIs

Up to 4× faster than Apple's MLX (mlx-lm), 1.5× on a typical task, same weights (measured 2026-10-04). Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents.

## Facts
- Website: https://rapidmlx.com
- Made by: raullenchai
- Category: AI agents & assistants
- GitHub: https://github.com/raullenchai/Rapid-MLX (4116 stars)
- Stage: Live

Listing page: https://launchwoo.com/p/rapid-mlx
Listed on LaunchWoo, a directory of AI apps, developer tools and AI devices: https://launchwoo.com/launches