this post was submitted on 03 Apr 2026
24 points (63.3% liked)

Technology

84940 readers
3832 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
[–] madcaesar@lemmy.world 6 points 1 month ago (7 children)

What could this be used for?

[–] baatliwala@lemmy.world 10 points 1 month ago* (last edited 1 month ago) (6 children)

Local LLMs, probably even ones you can host on phones. But they won't be as powered of course

[–] madcaesar@lemmy.world 4 points 1 month ago (5 children)

Yea I get that, but does anyone have any practical ideas for local LLM?

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

In addition to what the others said, some apps allow you to link to an LLM model for additional features.

For eg Immich has prebuilt models you can choose depending on how powerful your PC is, which will give facial recognition and powerful NLP-like search capabilities for your library. So if they think this is model good they can make a new prebuilt one using this as a base. Software like Microsoft Teams uses LLM for better background blurring for video calls, so maybe an open source equivalent can make use of it.

Also you can use it for other stuff like image generation too

load more comments (4 replies)
load more comments (4 replies)
load more comments (4 replies)