MLX-Serve
Local LLM and media server for Apple Silicon that runs chat, coding agents, image, video, music and speech models offline via OpenAI-compatible API.
Not verified yet
How far pickfit got
pickfit hasn’t verified MLX-Serve yet, so there are no tested install steps.
What follows comes from its README only.
Use it
You need first
- Runtimes:
Zig - At least 16 GB of RAM
- Apple silicon only
What it does
pickfit hasn’t run it yet, so these come from the README only.
- Run coding agents like Claude Code locally against downloaded modelsNot tested
- Generate pictures, video, music, speech with voice cloning and 3D modelsNot tested
- Run large models streamed from SSD and share models over network/ThunderboltNot tested
Good for
- run chat and coding agents locally via OpenAI/Anthropic-compatible API
- generate images, video, music, speech and 3D models locally
- transcribe meetings with speech-to-text and speaker diarization
An alternative to Ollama.