MLX-Serve

Run local models through a native command-line server and browser console.
MLX-Serve provides OpenAI, Anthropic and Ollama-compatible HTTP APIs and
downloads models from Hugging Face.

This Linux package requires a supported NVIDIA GPU and host driver 580 or
newer. It includes the CUDA runtime and supports amd64 and arm64 systems.
The optional system daemon is disabled until explicitly configured.