LM Studio

Use models running in LM Studio on your computer.

Overview

LM Studio is a desktop app for running open models, and it can serve them to other devices on your network.

1
Install LM Studio and download a model.
2
Open the Developer tab, load a model and start the server. Its default port is 1234. (In the command line: lms server start.)
3
In the server settings, turn on Serve on Local Network. Allow it through the firewall if asked, on your private network.
4
Note the network address LM Studio shows, for example 192.168.1.20.

Cost. Free. You use your own computer’s power.

1
Open Loom, then Providers in the menu, and choose Add provider.
2
Pick LM Studio (the search box finds it).
3
Fill in the fields in the table below.
4
Choose Connect. Loom checks the key and says how many models it found. If it cannot check, it says so, and you can Save anyway and try a message.
5
Open the model chip below the message box and pick a model.

Field in Loom	What to put	Needed
Endpoint	`http://localhost:1234/v1`	Pre-filled
Name	Anything you like. It is shown in the model picker	Optional

Appears in Loom as	LM Studio
Sign-in	None (any key is ignored)
Models	Loom fetches the list from your account
Tools (connectors, search)	If the server and model allow it
Photos	Depends on the model
PDFs	No

Keep the server on your own network; it has no password by default.

What you see	What to do
Can’t connect	Make sure the server is running and “Serve on Local Network” is on, the phone is on the same Wi-Fi, and the address includes `:1234/v1`.
Model not found	Type the model name exactly as the server lists it.