Instant Message with SmartestChild

A Large Language Model that runs entirely in the browser with WebGPU.

No data is sent to the server. Conversations are cached in local storage.

WebGPU is only supported in Desktop Google Chrome 113

Powered by Apache TVM and MLC Relax Runtime. Vicuna trained by LMSys

This will download the model and may take a few minutes. After the first time, it will be cached.
Vicuna 13B