News for hackers. Stuff that matters.

A comment on Nvidia Unveils RTX 5880 Graphics Card with 14,080 CUDA Cores and 48GB VRAM. Parent comment

Re:Nvidia Unveils RTX 5880 Graphics Card with 14,080 CUDA Co... by visarga on Sunday January 07, 2024 @03:39AM (#38899612)
That's why I provided the demo link, see the tokens/second. They are running LLaMA 70B at about 260T/s without quantization. This is the fastest LLaMA2 model
[ Parent | on HN ]

There are no comments on this comment yet.