this post was submitted on 17 Dec 2024
213 points (97.8% liked)

Technology

60085 readers
2747 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 content.
  3. Be excellent to each another!
  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, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 3 points 1 week ago (1 children)

Can’t you run LLMs on 4090/5090 maybe 5080? Basically any Nvidia card with 24GB+ of VRAM?

[–] [email protected] 9 points 1 week ago* (last edited 1 week ago) (2 children)

Yeah, but they not worth it.

The 4090 is basically just as good as the 3090 because it has the same amount of vram, but twice the price... so you mind as well get 2x 3090s.

The 5090 will be hilariously expensive, and 24GB -> 32GB is not that great, as you still can't run 70B class models in that pool... again, mind as well get 2x 3090s. I would not even bother trading my single 3090 for 5090.

If AMD sold a 48GB consumer card, you would see them dominate the open source LLM space in a month, because every single backend dev would buy one and get their projects working on them. Same with Intel. VRAM is basically the only thing that matters, and 24GB is kinda pitiful at a 4090's price.

[–] [email protected] 5 points 1 week ago

I'd already be happy if AMD goes with 24 GB on their upper midrange cards, but I would not be surprised if they stick with 16 GB. 48 GB seems extremely unlikely, unfortunately.

Doing LLMs with 8 GB is not fun, especially not with RDNA 2 which has so many issues with ROCm.

[–] [email protected] 1 points 1 week ago (1 children)

Halo has me hopeful that AMD are going to continue down this idea of having APUs that can use onboard RAM instead of requiring it to be built in. It'd be great to just be able to upgrade my RAM rather than replace a whole ass GPU.

[–] [email protected] 2 points 1 week ago* (last edited 1 week ago)

It uses embedded LPDDR5X, so it will not be upgradeable unless the mobo/laptop maker uses LPCAMMs.

And... that's kinda how it has to be. Laptop SO-DIMMs are super slow due to the design of the DIMMs, and they need crazy voltages to even hit the speeds/timings they run at now.