AI on your Mac

How to use LM Studio with LocalInbox for private email AI on Mac

Use a model you run in LM Studio for LocalInbox's summaries, suggested replies and drafts. Everything stays on your Mac, with no API key.

In short

Install LM Studio on your Mac, download a model and start its local server. Then in LocalInbox open Settings › Intelligence, set Written by to “A model server on this Mac” and click LM Studio. LocalInbox fills in http://127.0.0.1:1234/v1. Choose your model and click Test Connection.

LM Studio for macOS, from lmstudio.ai, and enough memory for the model you choose. Apple Intelligence isn't needed.

Steps

  1. Download LM Studio from lmstudio.ai, move it to Applications and open it.
  2. Download a model in LM Studio's model search.
  3. Start LM Studio's local server from its Developer tab, and load your model.
  4. In LocalInbox, open Settings › Intelligence and set Written by to “A model server on this Mac”.
  5. Click LM Studio. The address becomes http://127.0.0.1:1234/v1.
  6. Choose your model in the Model menu, or leave Server's first.
  7. Click Test Connection. It shows which model answered and how long it took.

Server settings

Server address: http://127.0.0.1:1234/v1, LM Studio's OpenAI-compatible address on your Mac. If you changed the server's port in LM Studio, use yours, ending in /v1.

Troubleshooting

Test Connection says nothing is answering

LM Studio's server isn't running. Start it from the Developer tab, then try again.

The Model menu is empty

Download a model in LM Studio first, then click the reload button next to the menu.

Summaries are slow

The first request may load the model into memory. If answers stay slow, try a smaller model.

Questions

Does my mail leave my Mac?

Not through LocalInbox: it accepts only a server address on this Mac (127.0.0.1, ::1 or localhost), skips any system proxy and follows no redirects. Choose a model that runs on your Mac, though. Some servers can also hand requests to models in the cloud, such as Ollama's cloud models, and LocalInbox can't see that happen.

What does the model write?

Summaries, suggested replies, Draft with AI, Rewrite and Ask your mailbox. Turn summaries and suggested replies off separately in Settings › Intelligence; what you ask for is still written. Sorting mail doesn't use the server.

Can I use LM Studio on another computer?

No. LocalInbox refuses any address that isn't on this Mac, so your mail never crosses the network to reach a model.