40
Hardware for local inference? (lemmy.ca)
submitted 5 months ago by to c/selfhosted@lemmy.world
25 comments fedilink hide all child comments
 

I want to host some LLM's locally and use more advanced models. Since new hardware is out of the question, I think I should be able to pull something off buying some yesteryear equipment on ebay etc. Did anybody attempt such a project? Does it scale horizontally? (I.e. can I connext two boxes to overcome single box slowness?)

you are viewing a single comment's thread
view the rest of the comments
[–] 8 points 5 months ago (2 children)

The trend I see are the Mac Minis with a lot of unified memory. These are typically very well off people though. Prices for even old GPUs like 3090s are ridiculous now. I don't think connecting 2 machines over Ethernet would work well, but putting 2 GPUs in a single machine does.

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] 2 points 5 months ago

    I bought a used 3090 two years ago, and back then they were usually listed for €800-1000 in my country. I thought I was lucky to find one for €700 after searching for a few months, and I don't think they've ever been cheaper than this here. There are definitely fewer of them available now, but you can still buy one for €950 (and possibly even lower if you're patient). So prices have gone up, but IMO not by ridiculous amounts like RAM.

  • permalink
  • fedilink
  • source
  • parent