LocalLLaMA

3 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago

MODERATORS

communick@poweruser.forum

Is it worth using a bunch of old GTX 10 series cards ( like 1060 1070 1080 ) for running local LLM? (alien.top)

submitted 11 months ago by dpak90@alien.top to c/localllama@poweruser.forum

10 comments fedilink hide all child comments

Was wondering if theres anyway to use a bunch of old equipment like this to build an at home crunch center for running your own LLM at home, and whether it would be worth it.

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

[–] 512DuncanL@alien.top 1 points 11 months ago (1 children)

You might as well use the cards if you have them already. I'm currently getting around 5-6 tokens per second when running nous-capybara 34b q4_k_m on a 2080ti 22gb and a p102 10gb (basically a semi lobotomized 1080ti). The p102 does bottleneck the 2080ti, but hey, at least it runs at a near usable speed! If I try running on CPU (I have a r9 3900) I get something closer to 1 token per second.

[–] FullOf_Bad_Ideas@alien.top 1 points 11 months ago (1 children)

How did you get your 2080 ti to 22gb of VRAM?

[–] 512DuncanL@alien.top 1 points 11 months ago

Modded cards are quite easy to obtain in china