Re:Meta Llama 3
by cjbprime on Thursday April 18, 2024 @10:59PM
(#40083061)
Oh cool! But at the cost of twice the VRAM and only having 1/8th of the context, I suppose?
[ Parent
| on HN ]
Llama 3 70B takes half the VRAM as Mixtral 8x22B. But it does need almost twice the FLOPS/bandwidth. Yes, Llama's context is smaller although that should be fixable in the near future. Another thing is that Llama is English-focused while Mixtral is more multilingual.