What you need
LM Studio installed, with at least one model downloaded. LM Studio needs a Mac with Apple silicon.
Set it up
- Open LM Studio and download a model if you haven’t yet.
- In LM Studio, turn on its local server (the Developer tab). Infinity looks for it at
localhost:1234. - In Infinity, open Settings ▸ Accounts and models ▸ LM Studio. Your LM Studio models appear in the model menu.
- Pick one and start a chat. Nothing leaves your Mac.
Good to know
- If LM Studio’s server asks for an API token, create one in LM Studio (Developer ▸ Server settings), then paste it in Infinity’s Settings under LM Studio.
- Infinity can also open a model’s page in LM Studio from Find models.
Stuck?See common fixes, or tell us what happened.
Other guides
Ollama · Apple Intelligence · MLX LM · Your ChatGPT plan · Your Claude plan · OpenAI · Anthropic · Google Gemini · OpenRouter · Hugging Face · Groq · Mistral · xAI · Together AI · Any OpenAI-compatible server