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

communick@poweruser.forum

Anyone know what the speed difference between 2x 4090 vs 2x 3090 would be for larger LLMs (70B-120B) (alien.top)

submitted 9 months ago by asdfgbvcxz3355@alien.top to c/localllama@poweruser.forum

2 comments fedilink hide all child comments

Probably stupid of me but I just bought a second 4090 for larger LLMs and was wondering if that was any faster than just having bought two 3090s

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

[–] Dry-Vermicelli-682@alien.top 1 points 9 months ago

Honestly.. for $2K or so a pop for 4090s.. I'd have bought the M3 MAx Pro laptop with 128GB RAM. Video the other day showed it could load and work with 70b LLM just fine, but a single 4090 was not able to. Dual with 48GB ram probably can, but will likely be slower.. and having a top of the line laptop that doubles as a pretty beefy AI run box for about the same price seems like better money spent.