logoalt Hacker News

DeathArrowtoday at 5:43 AM1 replyview on HN

Quality of answers from quantized models is noticeable worse than using the full model.

You'll be better using Qwen 3.6 Plus through Alibaba coding plan.


Replies

SoMomentarytoday at 11:49 AM

> Quality of answers from quantized models is noticeable worse than using the full model.

This is the very reason I've heard I shouldn't use Alibaba!