ⓘ
✅ Ready! Click "Generate" to load the model and start chatting.
First-time loading note: The model is ~2 GB and may take 30-60 s to download. Subsequent visits are faster thanks to browser caching.
First-time loading note: The model is ~2 GB and may take 30-60 s to download. Subsequent visits are faster thanks to browser caching.
This demo runs entirely in the browser using the
@xenova/transformers library. No data leaves your device.
Developed as a lightweight, privacy-focused demonstration of browser-based LLMs.