MTPLX

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Community maintained hardware plugin for vLLM on Apple Silicon

Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar