this post was submitted on 09 Apr 2025
38 points (79.7% liked)

Selfhosted

46168 readers
779 users here now

A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.

Rules:

  1. Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.

  2. No spam posting.

  3. Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it's not obvious why your post topic revolves around selfhosting, please include details to make it clear.

  4. Don't duplicate the full text of your blog or github here. Just post the link for folks to click.

  5. Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).

  6. No trolling.

Resources:

Any issues on the community? Report it using the report flag.

Questions? DM the mods!

founded 2 years ago
MODERATORS
ruud@lemmy.world
Loki@lemmy.world
CannaVet@lemmy.world
devve@lemmy.world
HybridSarcasm@lemmy.world
HybridSarcasm@lemmy.hybridsarcasm.xyz
38
How to use GPUs over multiple computers for local AI? (lemmy.dbzer0.com)
submitted 1 week ago by marauding_gibberish142@lemmy.dbzer0.com to c/selfhosted@lemmy.world
64 comments fedilink hide all child comments
 

The problem is simple: consumer motherboards don't have that many PCIe slots, and consumer CPUs don't have enough lanes to run 3+ GPUs at full PCIe gen 3 or gen 4 speeds.

My idea was to buy 3-4 computers for cheap, slot a GPU into each of them and use 4 of them in tandem. I imagine this will require some sort of agent running on each node which will be connected through a 10Gbe network. I can get a 10Gbe network running for this project.

Does Ollama or any other local AI project support this? Getting a server motherboard with CPU is going to get expensive very quickly, but this would be a great alternative.

Thanks

you are viewing a single comment's thread
view the rest of the comments
[–] False@lemmy.world 5 points 1 week ago (2 children)

You're entering the realm of enterprise AI horizontal scaling which is $$$$

[–] marauding_gibberish142@lemmy.dbzer0.com 2 points 1 week ago (3 children)

I'm not going to do anything enterprise. I'm not sure how people seem to think of it this way when I didn't even mention it.

I plan to use 4 GPUs with 16-24GB VRAM each to run smaller 24B models.

[–] False@lemmy.world 6 points 1 week ago (1 children)

I didn't say you were, I said you were asking about a topic that enters that area.

[–] WhyJiffie@sh.itjust.works 4 points 1 week ago (1 children)

well that looks like small enterprise scale

[–] marauding_gibberish142@lemmy.dbzer0.com 1 points 1 week ago (1 children)

If you consider 4 B580s as enterprise, sure I guess

[–] WhyJiffie@sh.itjust.works 1 points 1 week ago

not that, but 4 GPUs with 16-24GB VRAM I do

[–] Xanza@lemm.ee 0 points 1 week ago (1 children)

I’m not going to do anything enterprise.

You are, though. You're creating a GPU cluster for generative AI which is an enterprise endeavor...

[–] marauding_gibberish142@lemmy.dbzer0.com 2 points 1 week ago

Specifically because PCIe slots go for a premium on motherboards and CPU architectures. If I didn't have to worry about PCIe I wouldn't care about a networked AI cluster. But yes, I accept what you say