this post was submitted on 21 Sep 2026
641 points (98.5% liked)

Technology

88199 readers
3958 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
you are viewing a single comment's thread
view the rest of the comments
[–] SabinStargem@lemmy.today 2 points 9 hours ago* (last edited 9 hours ago)

It depends on what backend you are using. UnSloth Desktop and KoboldCPP allow you to use multiple GPUs, alongside leveraging your RAM.

Unfortunately, Hermes Agent doesn't allow you to control and leverage your GPUs as of yet.

If you are using ComfyUI, there is an extension called Distribution, if you are getting into picture generation. You can order up batches of pictures, and each card tackles a different one.

In the case you want to hook up your backend to another program for agentic purposes, I recommend UnSloth Desktop. I have been using it with Lingua Gacha to translate a RPGMaker game. KoboldCPP isn't able to handle this kind of work yet, unfortunately.