Gemma 4 E2B runs locally in Chrome desktop browser using WebGPU; TurboQuant algorithm compresses AI model 2.4x, generates diagrams at 30+ tokens per second without server or API key

Prompt → Diagram — Gemma 4 E2B in desktop Chrome (WebGPU)

TurboQuant Prompt → Diagram Describe any diagram, Gemma 4 E2B generates it as Excalidraw — entirely in your browser. Desktop Chrome 134+ only. The LLM outputs compact code (~50 tokens) instead of raw Excalidraw JSON (~5,000 tokens). The TurboQuant algorithm (polar + QJL) compresses the KV cache ~2.4× so longer conversations fit in GPU memory. Needs WebGPU subgroups (Safari/iOS not supported yet) and ~3 GB RAM (mobile browsers cap well below this). This demo reimplements the TurboQuant algorithm ...