Using LM Studio
Run local language models in 120 AI Chat or 120 HN through LM Studio.
What you need
- A computer that can run both your 120.dev app and LM Studio.
- 120 AI Chat or 120 HN.
- An internet connection to download LM Studio and models.
On macOS, LM Studio requires Apple silicon and macOS 14.0 or later. Intel Macs are not supported. Check the current LM Studio system requirements, including Windows hardware requirements, before installing.
Install LM Studio
- Download the installer for your operating system from LM Studio.
- On macOS, open the
.dmgand drag LM Studio into Applications. On Windows, run the installer and follow its prompts. - Open LM Studio.
LM Studio is a desktop app for downloading and running AI models locally.
Download a local model
- Use LM Studio's model search to find a model that fits your computer's memory and storage.
- Download the model variant you want to use.
- Load the downloaded model in LM Studio.
Download size and memory use depend on the model variant, quantisation, and context length. Follow LM Studio's model download guide if you need help choosing or loading a model.
Start the local server
- Open the Developer tab in LM Studio.
- Turn on Start server.
- Keep LM Studio running while you use the model in your 120.dev app.
See the local server guide for server settings and troubleshooting.
Connect your 120.dev app
- Open 120 AI Chat or 120 HN, then go to Settings > AI Providers.
- Select Configure beside LM Studio.
- Check that API URL is
http://localhost:1234for a standard local installation. - Select Connect to load the available models. If you changed the URL, select Save to keep it.
- Choose a model in the app.
A standard local LM Studio server does not require an API key.
Use account features
Basic AI Chat conversations work without signing in. Sign in through Settings > Account to use attachments, web search, and parallel threads, or to use AI summaries in 120 HN. Use your usual 120.dev account.
Local processing and internet access
When you use a local model through a server on your computer, model processing takes place on your device. Downloads, account sign-in, updates, and online features such as web search still require internet access. You may need to reconnect periodically to refresh account access.
Example local models
For an example of model variants available for LM Studio, see the Qwen3 4B GGUF model card and its list of files. You do not need to use this model; choose one that fits your computer and task.
Download size and memory requirements depend on the model variant, quantisation, and context length. Check the selected model's details and LM Studio's memory estimates instead of relying on a fixed size or RAM estimate for an entire model family.