Skip to the page

Providers

LM Studio

Your LM Studio models, here

The models you already have in LM Studio, running right here — private, free and offline. Conch starts LM Studio’s server when it needs to.

  • Private
  • Free
  • Works offline
Connects with
A program on this computer
Your apps
Conch hands it their tools
To start
Free
  • NoYour files and commands
  • YesSaves memories itself
  • YesAsks before each step
  • YesWorks offline

Worth knowing first

  • A model runs at your computer’s speed; the first answer waits while LM Studio loads it.
  • Tool-capable models can use Conch’s files and connected apps. Commands need the OS sandbox and run without network access; chat-only models cannot take actions.

Connect it

  1. Open Settings → Providers and choose LM Studio.
  2. If it isn’t here, press Install LM Studio. Conch uses winget or Homebrew, or links to it on Linux.
  3. Download a model in LM Studio. It shows up in the picker.

Conch finds LM Studio's server on whatever port it last used, and starts it if it's off.

What you get

Your LM Studio models, private, free and offline. Conch asks what each can do (pictures, tools, thinking) and leaves out embedding models. Models that call tools get your apps, memory, skills and the browser. Anything that changes asks first.

Good to know

  • A small model gets a lean setup: short instructions, and tools as it needs them. Load it with a bigger context length in LM Studio, and Conch uses it.
  • The first answer waits while LM Studio loads the model. Conch says so in the chat.
  • A key, only if you turned one on. With Require Authentication on, create a token under Developer → Server Settings → Manage Tokens and paste it on LM Studio’s page in Conch.
  • It answers offline, and can take over a chat when the internet drops. See Offline and at a limit.