LUXR.AI
⚡ REAL LLM 🔒 100% PRIVATE
Real Generative AI · Runs In Your Browser
✓ Model cached — loading instantly from your device
Starting engine…
SmolLM2-360M is a real transformer LLM. Downloads once (~200MB), then lives on your device forever — instant on every future visit.
No GPU detected. Falling back to CPU/WASM mode — works on all browsers, slightly slower.
For best speed use Chrome 113+ or Edge 113+ on desktop.
Real Generative AI · Token Streaming · Zero Servers

ASKLUXR.AIANYTHING

A real transformer LLM running in your browser. Streams tokens live like GPT. No API, no server, no data leaves your device.

✍ Blog post
💡 Startup ideas
📐 Explain AI
✉ Draft email
⚙ Write code
🎭 Short story
∑ Math
🌐 Translate
ENTER to send · SHIFT+ENTER for new line · Model runs on your device