this post was submitted on 17 Dec 2024
184 points (97.4% liked)

Technology

59979 readers
3950 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
[–] brucethemoose 4 points 20 hours ago* (last edited 20 hours ago) (1 children)

Qwen 2.5 32B is where it's at now. 24GB is affordable, and it fits perfectly.

Otherwise, stay on the lookout for AMD Strix Halo, which can reportedly allocate up to 96GB on its IGP, and you can run faster backends like vllm or exllama.

[–] [email protected] 1 points 18 hours ago (1 children)

What's up with Qwen that makes it better than anything else?

[–] brucethemoose 4 points 18 hours ago* (last edited 18 hours ago)

It's just smarter with the same number of parameters. Try Qwen QwQ or Qwen coder 32B, see for yourself... it stacks up well against huge models like the 123B Mistral Large, or even GPT-4.

Why? Alibaba trained it well, presumably with better data than OpenAI or whomever else, though specifics are up for debate. Some suggests that bilingual training on English/Chinese (aka the two largest text corpuses in existance) significantly helps the model over mostly english. Some say the government just gave them better data. There's also suggestions that having so few GPUs compared to American AI companies made the Chinese "thrifty," and gave them far more incentive to be innovative rather than brute forcing models (which has diminishing returns).