Quick Start

Get started with local large models in just a few simple commands.

Run your first model

# Run a model — downloads, starts server, and chats (all automatic)
csghub-lite run Qwen/Qwen3-0.6B-GGUF

Search for models

You can search for models on CSGHub directly from your terminal:

csghub-lite search "qwen"

Check running models

Models stay loaded in memory for 5 minutes by default after exiting (configurable) for instant reconnection.

csghub-lite ps

Login to CSGHub (Optional)

If you need to access private models, log in first:

csghub-lite login

Interactive Chat Commands

Once in a chat session (via run or chat):

Command	Description
/bye, /exit, /quit	Exit the chat
/clear	Clear conversation context
/help	Show help

End a line with \ for multiline input. Press Ctrl+D to exit.