Selfhosted

39435 readers

2 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:

Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.
No spam posting.
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.
Don't duplicate the full text of your blog or github here. Just post the link for folks to click.
Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).
No trolling.

Resources:

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

Questions? DM the mods!

founded 1 year ago

MODERATORS

[email protected]

What would be the cheapest and most cost-effeciant way of self hosting LLMs (lemmy.world)

submitted 5 months ago by [email protected] to c/[email protected]

21 comments fedilink hide all child comments

I've a minipc running an AMD 5700U where I host some services, including ollama and openwebui.

Unfortunately the support of rocm isn't quite there yet and not to mention that of mobile GPUs.

Surprisingly the prompts work when configured to use the CPU, but the speed is just... well, not good.

So, what'd be a cheap and energy efficient setup to run sone kind of LLM for personal use, but still get decent speed?

I was thinking about getting an e-gpu case, but I'm not sure about how solid this would end up.

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 9 points 5 months ago (2 children)

Chinese mining motherboard with any xeon cpu (because of abundance of PCI lanes in cpu) and 12x16gb nvidia p100 and nvlink bridges (p40 gives 24gb of vram but doesn't have nvlink capabilities and slower gddr5 memory, p100 have hbm memory on the contrary which is good for llm) and 8x64gb ddr4 ecc ram, if you buy gpus from ebay and other components such as motherboard, CPU, ram, and ssd from AliExpress it comes quite cheap

[–] [email protected] 1 points 5 months ago (2 children)

Aren't those all old-ish sockets with Xeons that top out at like 40 PCIe lanes?

[–] [email protected] 2 points 5 months ago

Problem is, new i7/i9 top out at 24 pcie lanes so old xeons is still bang for the buck in homelab sector

[–] [email protected] 2 points 5 months ago

Mining boards give about 1-2 pci lanes per gpu because there's a lot of gpus, also look up Nvidia mining gpus, they restricted to pcie x1 or/and x4 even if you put them into x16 slot

[–] [email protected] 1 points 5 months ago* (last edited 5 months ago)

Jesus. Kinda overkill depending on how many parameters the model is and the float precision