Skip to content

Top New Best Ask Show Jobs

DeepSeek-R1 at 3,872 tokens / second on a single Nvidia HGX H200 (opens in new tab)

(blogs.nvidia.com)

13 pointsmoondistance1y ago1 comments

DeepSeek-R1 at 3,872 tokens / second on a single Nvidia HGX H200 | Better HN

1 comments

billconan1y ago

https://news.ycombinator.com/item?id=42879864

this is cerebras' 70B number, 1600 tokens / sec, not sure about the costs.

j / k navigate · click thread line to collapse