Run Claude Code locally for free: mlx-serve on Apple Silicon

A developer released mlx-serve, a native Zig server for MLX-format language models on Apple Silicon, enabling local, free, and private use of AI coding assistants like Claude Code. The server exposes OpenAI, Anthropic, and Ollama-compatible APIs from a single binary, achieving 35% faster decode than LM Studio on Gemma 4 E4B 4-bit. It requires no Python, conda, or Docker, and can be installed via Homebrew.

Claude Code is the best AI coding assistant available right now. But it calls the Anthropic API by default, which adds up fast on long sessions. What if you could run it entirely locally - free, private, and on hardware you already own? mlx-serve makes this possible on any Apple Silicon Mac. mlx-serve is a native Zig server for MLX-format language models on Apple Silicon. It exposes OpenAI-compatible, Anthropic-compatible, and Ollama-compatible HTTP APIs - all on a single port, from a single binary. brew install mlx-serve That's it. No Python. No conda. No Docker. Claude Code looks for ANTHROPIC BASE URL and ANTHROPIC API KEY in your environment. mlx-serve implements the full Anthropic Messages API, so you just point Claude Code at it: export ANTHROPIC BASE URL=http://localhost:8080 export ANTHROPIC API KEY=local export ANTHROPIC DEFAULT MODEL=mlx-serve mlx-serve --model ~/.mlx-serve/models/mlx-community/gemma-4-e4b-it-4bit --serve Then launch Claude Code as normal. Streaming, tool calls, thinking blocks - all work. Full setup guide: https://mlxserve.com/claude-code-local/ https://mlxserve.com/claude-code-local/ On Apple Silicon, mlx-serve achieves 35%+ faster decode than LM Studio on Gemma 4 E4B 4-bit. The server is written in Zig with no Python runtime overhead. /api/chat , /api/generate , /api/embed endpoints - works with Raycast, Open WebUI, Obsidian