raullenchai/vllm-mlx

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. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

3 best points · 1 comments · 1 Hacker News post · 4,106 GitHub stars · View on GitHub

Hacker News discussions

• vLLM-mlx – 65 tok/s LLM inference on Mac with tool calling and prompt caching (3 points, 1 comments, by raullen, 2026-02-26)