RUNTIME / EASY

LM Studio

Discovering, downloading and testing models without a terminal

DifficultyEasySetup profile

Platforms4apple · nvidia · amd · intel

APIOpenAI-compatible local server:1234

01 / INSTALL & RUN

1
InstallDownload the desktop app from lmstudio.ai
2
Start a modelSearch google/gemma-3-1b-it in Discover → Load → Start Server
3
Connect your app
OpenAI-compatible local server · :1234. Keep the service bound to localhost unless you add authentication and network controls.

Watch out

The app minimum requirements are not a model-fit guarantee. Leave memory for the OS and context cache.

02 / COMPATIBLE MODELS