AFAIK you would get about ~5 concurrent users, with a max context window of ~128K tokens on the larger models.
This wouldn't be good enough for coding -- are you guys thinking of using it for something else?
Roughly equivalent to 4x H200's for less than half the price.
Vaguely around 60k tokens per second...
AFAIK you would get about ~5 concurrent users, with a max context window of ~128K tokens on the larger models.
This wouldn't be good enough for coding -- are you guys thinking of using it for something else?