logoalt Hacker News

ukblewistoday at 8:53 PM1 replyview on HN

You are aware that a 1 trillion parameter model won’t run on any quantity of consumer hardware, even heavily quantized… you need a data center for that. And that is not even to talk of the Kimi K3 model which is in the ballpark of 3 trillion


Replies

layla5alivetoday at 9:09 PM

You do not need a data center - just a single rack will do to run it fast. Or about 100x 5090s.