String Hopper
Tutorials

Connect a local model

Use a model server running on your Mac instead of Apple's on-device model. Any server with an OpenAI-compatible /v1 API works.

Before you start

Start a model server with a model loaded. See Set up a server for LM Studio, Ollama, llama.cpp and MLX, and Choose a model if you have not picked one.

  1. Open Settings

    Click Settings at the bottom of the sidebar, or press ⌘,.

  2. Choose the local model option

    Under Your stylist, click A local model you run. A card named Your local model appears below.

    Settings with A local model you run selected and the Your local model card belowSettings with A local model you run selected and the Your local model card below
  3. Enter the server address

    Type the address in Server address. It must start with http:// or https:// and usually ends in /v1. Your server shows its address when it starts.

    Or click the ? button beside the field and pick one of the usual defaults:

    ServerDefault address
    LM Studiohttp://localhost:1234/v1
    Ollamahttp://localhost:11434/v1
    llama.cpphttp://localhost:8080/v1
    vLLM / MLX serverhttp://localhost:8000/v1
    Splashhttp://127.0.0.1:8000/v1

    Leave Key empty unless your server requires one.

    The address help popover listing the default server addressesThe address help popover listing the default server addresses
  4. Pick the model

    After the server answers, Model shows a list of the models it is serving. Choose one. After you load a different model on the server, click the circular-arrow button to refresh the list.

  5. Check what happens to photos

    Below the model, Settings shows whether the model can look at photos. The app detects this. See Photos: can your model see?

  6. Test the connection

    Click Test connection. A green dot and Local model ready, followed by the model's name, means the connection works.

    Your local model card with a model chosen and the status Local model readyYour local model card with a model chosen and the status Local model ready
  7. Try it

    Run a lens. To check a model more thoroughly, use the five-minute check.

Switch back to Apple's model

In Settings, under Your stylist, click Apple's on-device model. Your local settings are kept.

If the connection fails

See Local model in Troubleshooting for each message and its fix.