MicroLLM Lab – Try 7 tiny LLM's in the browser

一句话概要

Run Q4 small language models entirely in the browser with WebGPU. Chat, benchmark, and compare PetitGPT, SmolLM2, and friends on-device.

原文开头节选

Objective checks (regex / exact tokens), not writing quality. A 135M model is allowed to fail — that is the measurement. Pick models, then run. Estimate uses your last tok/s if we have one.

Generate and download a verifiable performance certificate with your device hardware, peak and sustained tokens/second, and share your score.

The editor is eval() ’d in this origin, then each check runs on the model’s decoded text.

(以上为原文节选,完整内容见下方”原文来源”)

这条动态今日登上 Hacker News 首页(86 赞 / 31 评论,来源 stateofutopia.com)。技术雷达每日自动聚合 AI 工程、后端架构、DevOps 方向的前沿动态;相关工程落地可浏览下方的相关服务与延伸阅读,或直接与我们团队交流。