Local LLM Runner

Run AI models privately in your browser using WebGPU.

100% Private (No Server Uploads)
Model
Initializing...
👋 Hi! I'm a local AI running entirely in your browser. Select a model and start chatting!

Note: First load requires downloading model weights (1-4GB). Please be patient.

Running LLMs Locally with WebGPU

Run powerful AI models like Llama 3 and Gemma directly in your browser using WebGPU.

System Requirements

Requires a GPU-enabled device and a modern browser (Chrome/Edge 113+).

Local LLM FAQ

Is my data private?

Yes, the model runs entirely on your device. No data is sent to any server.

Why is it slow?

Performance depends on your GPU. Initial load times may be long as the model weights are cached.