News for hackers. Stuff that matters.
Re:Qwen3.8-Max: A New Bar for Coding and Cowork by npodbielski on Monday August 03, 2026 @01:49AM (#49151672)
In my case I would say they are comparable but moe models are looping and getting lost a lot more than dense models.

On the other hand having 90t/s with any local model is nice and Pi with loop police extension can prevent looping a lot.

Re:Qwen3.8-Max: A New Bar for Coding and Cowork by cyanydeez on Monday August 03, 2026 @10:09AM (#49156021)
Looping seems related to quantization and not the model itself. If youre digging deep into quants to get working context then yeah.