874
The Pollution Being Churned Out by AI Data Centers Is So Severe That It's Almost Incomprehensible (futurism.com)
submitted 2 months ago by to c/technology@lemmy.world
159 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 2 months ago (1 child)

if you start excluding the 1000+ B param models ..
using smaller models, would initially ease hardware demand by 60% .
OFC you cant.. and probably shouldnt, ignore and disrespect SOTA flagship models

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 2 points 2 months ago*

    Even "big" open source models like DSV4 and Ling/Ring are very efficient. They're big, but (seemingly) sparser than US models, so they're cheap.

    They run surprisingly well with hybrid CPU+GPU inference on desktops. And thats not even getting into the efficient attention mechanisms.

    I can run DSV4 Flash, barely quantized, with ~1M context on my Ryzen desktop at ~11 tokens/s. If you told me that two years ago, I would not have believed you.

  • permalink
  • fedilink
  • source
  • parent