LocalLLaMA

1 readers

1 users here now

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

founded 10 months ago

MODERATORS

submitted 10 months ago by Training_Wait_3904@alien.top to c/localllama@poweruser.forum

4 comments fedilink hide all child comments

Are these worth bothering with? Or money better spent on 2x3090 or A6000?

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

[–] a_beautiful_rhind@alien.top 1 points 10 months ago

3090s are faster. P40s are mostly stuck with GGUF. P100s are decent for FP16 ops but you will need twice as many.

All depends on what you want to do. 8 cards are going to use a lot of electricity and make a lot of noise.