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

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

I tried it. Something like 1.2 tokens inference on lamma 70b with a mix of cards (but 4 1080s). Would process would crash occasionally. Ideally every card would have the same vram.

Going to try it with 1660 TI's. I think it may be the 'sweet spot' in power to price to performance.

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

Did you use some q3 gguf quant with this?