Mlx-serve – LLM inference server for Apple Silicon, written in Zig

Show HN: Mlx-serve – LLM inference server for Apple Silicon, written in Zig

Mlx-serve – LLM inference server for Apple Silicon, written in Zig is active in the show hn launch space.

Profile

Native Zig inference server for Apple Silicon. Runs any LLM — MLX and GGUF — faster than LM Studio. OpenAI- and Anthropic-compatible (Claude Code) APIs. No Python. Drop-in alternative to LM Studio, Ollama, and llama.cpp on macOS. Gemma 4, Qwen 3.6, Llama 3, Mistral, DeepSeek V4 Flash — local, MIT-licensed.

As a business in show hn launch, Mlx-serve – LLM inference server for Apple Silicon, written in Zig is listed here with the public details available about it.

Directory data places it at the Show HN launch stage.

Website: mlxserve.com