logoalt Hacker News

operatingthetanyesterday at 8:59 PM2 repliesview on HN

Are we at the point where 2x 9070XT's are a viable LLM platform? (I know this has 4, just wondering for myself).


Replies

oceanplexianyesterday at 9:03 PM

These things don’t have Flash Attention or either have a really hacked together version of it. Is it viable for a hobby? Sure. Is it viable for a serious workload with all the optimizations, CUDA, etc.. Not really.

cyanydeezyesterday at 10:59 PM

I'd go with strix halo if you're looking at that old of tech.

the latest AMD GPUs are RX 9070 XT w/32GB each