HN
Hacker News
Top
New
Best
Ask
Show
Jobs
Comment by kurtoid | Hacker News Reader
Parent
Full thread
kurtoid
·
Silly question: how does OpenAI host/serve it?
View on HN
magixx
·
I think on professional hardware you can get 80G of memory per GPU and they can likely do memory pooling.
Reply on news.ycombinator.com