Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

Source: Hacker News

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×, allowing longer conversations to fit in GPU memory.
• Requires WebGPU subgroups (Safari/iOS not supported yet) and ~3 GB RAM (mobile browsers cap well below this).

This demo reimplements the TurboQuant algorithm in WGSL compute shaders so it runs on the GPU at 30+ tok/s. The sibling turboquant‑wasm npm package implements the same algorithm in WASM + SIMD for CPU‑side vector search.

Resources

• All demos
• npm package
• GitHub repository