logoalt Hacker News

nicce • today at 8:57 AM • 0 replies • view on HN

Based on translating their Chinese text on Firefox, it says "per card":

> The current service throughput of a single cluster is 155 trillion tokens per day, and the overall revenue is $38 per hour (at the lowest price) per card.

With Kagi translate (best), it says GPU

> A single cluster currently serves 155 trillion tokens per day, generating overall revenue of $38 per GPU per hour (at off-peak electricity rates).

https://zhuanlan.zhihu.com/p/2095560295930508953