this post was submitted on 20 Aug 2026
391 points (99.5% liked)

Programmer Humor

32876 readers
586 users here now

Welcome to Programmer Humor!

This is a place where you can post jokes, memes, humor, etc. related to programming!

For sharing awful code theres also Programming Horror.

Rules

founded 3 years ago
MODERATORS
Feyter@programming.dev
anzo@programming.dev
BurningTurtle@programming.dev
pylapp@programming.dev
391
My home server was a totally justified purchase (lemmy.world)
submitted 17 hours ago by GolfFoxtrotLima@sh.itjust.works to c/programmer_humor@programming.dev
34 comments fedilink hide all child comments
 

cross-posted from: https://lemmy.world/post/50893918

you are viewing a single comment's thread
view the rest of the comments
[ā€“] Mika@piefed.ca 2 points 11 hours ago (1 children)

128 gb uram šŸ¤¤

Fucking saved.

Do you know what kind of open weights it can run, and at which t/s?

[ā€“] TropicalDingdong@lemmy.world 1 points 11 hours ago (1 children)

Yeah I can run any open weight models which leave me enough vram to not crash. But its a bit of a gotcha because you also need enough system ram to load the model. I use it to heavily parallelize training tasks.. Honestly, I need to tinker with it more but I'm pretty annoyed at how ollama has gone deep in the paint as basically being a tool for accessing cloud models.

Someday TM

[ā€“] dubs@lemmy.dbzer0.com 1 points 8 hours ago

Iā€™m pretty annoyed at how ollama has gone deep in the paint as basically being a tool for accessing cloud models.

Can you expound a little more on what you mean by this?

I like ollama, but I only really use it to load models and then hit the API. My current issue with them is that they don't seem to support non-text base interaction very well.