this post was submitted on 06 Feb 2025
428 points (100.0% liked)

Technology

67825 readers
5171 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 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] ZILtoid1991@lemmy.world 44 points 1 month ago (2 children)

And that's why you use local instances...

[–] oysterenjoyer@sh.itjust.works 2 points 1 month ago (1 children)

True, but you need powerful server in order to run the most capable Deepseek model, which most people don't have.

[–] brucethemoose@lemmy.world 7 points 1 month ago (1 children)

That’s an understatement. It won’t even fit well in 8xA100, you need an EPYC server to run it in CPU RAM, very slowly.

[–] Hackworth@lemmy.world 2 points 1 month ago* (last edited 1 month ago)

To run the 671B parameter R1, my napkin math was something like 3/4 of a million dollars in hardware. But that (plus the much lower training cost) made this a millionaire's game rather than a billionaire's. Plus the distillations do seem better than anything else we have at the smaller sizes at the moment. That said, I'm more looking forward to the first use of deepseek's methods with google's Titan architectures.

[–] Wildly_Utilize@infosec.pub 1 points 1 month ago

2nd place is duck.AI in via tor browser