MLX

Native Zig inference server for Apple Silicon Macs that runs local LLMs with MLX and GGUF support, plus OpenAI- and Anthropic-compatible APIs. The page highlights one-click local setup, Ollama compatibility, agent tools, MCP support, and performance claims against LM Studio.

A lightweight CLI for running multiple local MLX models on Apple silicon. It serves OpenAI-compatible endpoints, supports both text-only and multimodal models, and can browse/download from Hugging Face.

Writekin is a Mac app that fine-tunes a local language model on your own writing and uses it to draft and rewrite text in your voice, with all processing kept on-device.