undefined | Better HN

0 pointslittlestymaar1mo ago0 comments

How can a medium-sized model like Deepseek-V4-Flash be cheaper than a much smaller models like Qwen3.5-35B-A3B.

It's five times bigger in both total and active parameters!

0 comments

I don’t know for sure, but I believe those larger models must be run on nVidia hardware (CUDA), while Deepseek-V4-* can be run on Huawei chips. My assumption is that there is less demand pressure on non-nVidia chips.

j / k navigate · click thread line to collapse

0 comments

Ancapistani1mo ago

j / k navigate · click thread line to collapse