Infinity Download

Setup guide · On your Mac

MLX LM in Infinity.

Apple’s fast engine for running open models on Apple silicon.

What you need

A Mac with Apple silicon. Models are saved in Hugging Face’s usual folder, ~/.cache/huggingface.

Set it up

  1. Open Settings ▸ Models by job or Find models and choose a model marked for MLX.
  2. Press install. Infinity installs MLX LM, downloads the model and starts it, in one step.
  3. Pick the model in the model menu and chat.

Good to know

  • vLLM works the same way. Infinity also finds Jan, llama.cpp and GPT4All if they’re on your Mac.
  • Gated models on Hugging Face need your Hugging Face token. Add it under Hugging Face in Settings.
Stuck?See common fixes, or tell us what happened.

Other guides

Ollama · LM Studio · Apple Intelligence · Your ChatGPT plan · Your Claude plan · OpenAI · Anthropic · Google Gemini · OpenRouter · Hugging Face · Groq · Mistral · xAI · Together AI · Any OpenAI-compatible server