853
submitted 1 day ago* (last edited 1 day ago) by inari@piefed.zip to c/technology@lemmy.world
you are viewing a single comment's thread
view the rest of the comments
[-] leanleft@lemmy.ml 1 points 1 day ago

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

[-] brucethemoose@lemmy.world 2 points 23 hours ago* (last edited 22 hours 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.

this post was submitted on 17 Aug 2026
853 points (100.0% liked)

Technology

87280 readers
2936 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots


founded 3 years ago
MODERATORS