robss2020/microllm-lab

Tiny LLMs, Q4, in the browser. WebGPU lab inspired by yangqi0/petitgpt.

1 best points · 0 comments · 1 Hacker News post · 53 GitHub stars · View on GitHub

Hacker News discussions

• Blooper or Real Small Model Benchmark – 3000 tokens/sec in your browser (1 points, 0 comments, by logicallee, 2026-09-21)