← All posts

Local Model Support via WebGPU

Run Gemma 4 E4B entirely in browser using WebGPU — no API keys, progressively loaded, locally cached.

Keating now runs entirely in your browser using WebGPU. Run Gemma 4 E4B locally without any API keys. The model loads progressively and caches in your browser for subsequent sessions.

Requires Chrome 113+ or Edge 113+ with WebGPU support. Model size: ~5GB cached locally.