logoalt Hacker News

hypfer • yesterday at 9:29 PM • 2 replies • view on HN

Kinda cool but also entirely useless given the limited VRAM.

The readme oversells it by pretending it would be something actually usable, when instead it is a cool achievement to make it happen.


Replies

none_to_remain • yesterday at 10:05 PM

A 20 tps Qwen3.8-27B at 2 bits quantization is limited but not useless. I've been putting one on "read this codebase and figure out XYZ" for me, where the typos are less consequential.

sheephess44 • today at 3:15 AM

[flagged]