Text AI · 100% Local

Chat

Run open-source LLMs entirely in your browser. No server, no API keys — powered by WebGPU.

Vision + Language
Unified Multimodal
201 Languages
Global Coverage
Reasoning
Code · Agents · Visual
Download: ~500 MB
Initializing model…
0%
Model weights are cached for future visits.
Q
Chat
Ready on WebGPU

Start a conversation

Type your message and press Enter.
The model runs entirely in your browser.

No chats are sent to a server. Everything runs locally in your browser. AI can make mistakes. Check important info.