News for hackers. Stuff that matters.

A comment on DeepX claims inference up to 100B parameters at less than 5 W. Parent comment

Re:DeepX claims inference up to 100B parameters at less than... by gunalx on Monday November 09, 2026 @04:08PM (#50432161)
Not really. Models of that size is reasonably often moe. It is also 100b even if it only has 20b active at a time.
[ Parent | on HN ]

There are no comments on this comment yet.