AI 日报hiw3c.com

MicroLLM实验室-在浏览器中尝试7个微型LLM

原文标题 · MicroLLM Lab – Try 7 tiny LLM's in the browser
Hacker News Top stateofutopia.com 网页快照
正文为英文,可一键机器翻译(仅首次需要等待)

Loading MicroLLM lab…

Initializing WebGPU engine & model catalog…

Loaded on this device: … (Saved in browser IndexedDB cache)

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.

Runtime per test (ms)

Accuracy per test

Speed (tokens/s, sustained decode, suite wall) and accuracy (pass rate on objective tests) from runs in this browser. Numbers stay on this machine. Charts use the latest suite per model.

Accuracy (latest suite)

Speed (mean tok/s)

Suite wall (ms)

Verified Benchmark Certificate & Social Share

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

Write a benchmark in JavaScript

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

Prompt for a larger LLM

Function form