🧠 Trillim Chat

Powered by Trillim — privacy-first, CPU-native local AI.
Model: Trillim/BitNet-TRNQ · Threads: 16 · Token timeout: 120 s

⏳ The model loads in the background. If you send a message while it's still loading, the request will wait automatically — no need to refresh.

Built with Trillim · Gradio · Runs 100 % on CPU.