logoalt Hacker News

scosmantoday at 3:51 PM1 replyview on HN

z.ai is using all Chinese hardware for flash: https://thenewstack.io/glm-5-3-flash-chinese-chips/

There are other providers with much faster inference, like BaseTen at >100t/s: https://openrouter.ai/z-ai/glm-5.3-flash#performance


Replies

malshetoday at 4:06 PM

How do I find out where the openrouter model providers' servers are located?

show 1 reply