Selfhosted

60177 readers

605 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:

Detailed Rules Post

Be civil.
No spam.
Posts are to be related to self-hosting.
Don't duplicate the full text of your blog or readme if you're providing a link.
Submission headline should match the article title.
No trolling.
Promotion posts require active participation, with an account that is at least 30 days old. F/LOSS without a paywall has exceptions, with requirements. See the rules link for details.

Resources:

selfh.st Newsletter and index of selfhosted software and apps
awesome-selfhosted software
awesome-sysadmin resources
Self-Hosted Podcast from Jupiter Broadcasting

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

Questions? DM the mods!

founded 3 years ago

MODERATORS

curbstickle@anarchist.nexus

curbstickle_lw@lemmy.world

Hardware for local inference? (lemmy.ca)

submitted 1 month ago by droopy4096@lemmy.ca 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

[–] ryokimball@infosec.pub 3 points 1 month ago (1 children)

How old we talking? I personally wouldn't go further back than 2000 series rtx. A friend has had good luck with Intel GPUs for 'cheap'.

No, you absolutely cannot scale horizontally for speed. VRAM is king, with local RAM being swappable with major speed penalties. SSD is even slower than that and all those are orders of magnitude faster than ant Ethernet you'll be connecting boxes together with. That's not to say clustering isn't an option, just that speed is going to be worse the more you scale out like that.

[–] droopy4096@lemmy.ca 1 points 1 month ago (1 children)

I've got some circa 2010 cards laying about with a 32Gb server that already has 8Gb carved out for TrueNAS, so essentially I could squeeze 16-24Gb out of it, but it's an older i5 Intel CPU

[–] robber@lemmy.ml 0 points 4 weeks ago (1 children)

Your biggest issue with 2010 cards will be software (inference engine) support, I assume.

[–] fhein@lemmy.world 1 points 4 weeks ago

2010 is ancient technology, according to wikipedia Nvidia released the 600 series in 2012.. Even if there was some inference engine supporting it then lack of computational speed and memory bandwidth would probably make it not worth the effort.