Quick Start
Experience local large models in just a few simple commands.
Running Your First Model
# Download, start the server, and begin chatting (all automatic)
csghub-lite run Qwen/Qwen3-0.6B-GGUF
Searching for Models
You can search for models on CSGHub directly in the terminal:
csghub-lite search "qwen"
Viewing Running Models
After exiting the chat, the model stays loaded in memory for 5 minutes by default (configurable) for instant reconnection next time.
csghub-lite ps
Logging into CSGHub (Optional)
If you need to access private models, login first:
csghub-lite login
Interactive Chat Commands
Inside a chat session (entered via the run or chat command), use the following built-in commands:
| Command | Description |
|---|---|
/bye, /exit, /quit | Exit chat |
/clear | Clear the current conversation context |
/help | Display help information |
Use \ at the end of a line for multiline input. Press Ctrl+D to exit as well.