Codetato Chat Hub
Start a conversation with local AI models running completely in your browser with hardware-accelerated WebGPU.
General ChatContext: 2KSize: ~650 MB
A highly popular, compact model trained on 3 trillion tokens. A great baseline for testing web-based LLMs.
Fast Inference
Uses WebGPU to utilize your local GPU for lightning-fast, hardware-accelerated processing.
100% Private
Your conversations are kept local. No chat history or data ever leaves your device.
In-Browser Run
The model runs entirely in your browser window. No server or backend API keys are needed.
Total Chats
0
Total Messages
0
Avg Messages/Chat
0.0
Most Used Model
—