Show HN: 使用 Gemma 4 E2B 在浏览器中运行 Prompt-to-Excalidraw 演示(3.1GB)
阅读原文· teamchong.github.io开发者发布了一个基于 Gemma 4 和 E2B 的 Prompt-to-Excalidraw 浏览器演示,支持通过自然语言提示直接生成 Excalidraw 手绘图表。该方案将 3.1GB 的 Gemma 4 模型完全部署在浏览器端本地运行,借助 E2B 沙箱环境实现前端 AI 推理,无需后端服务器支持。项目在 Hacker News 获得 101 个赞。
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 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.