this post was submitted on 25 Mar 2025
39 points (100.0% liked)

Technology

1089 readers
36 users here now

A tech news sub for communists

founded 2 years ago
MODERATORS
muad_dibber@lemmygrad.ml
39
DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI (venturebeat.com)
submitted 1 week ago by yogthos@lemmygrad.ml to c/technology@lemmygrad.ml
15 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] Philo_and_sophy@lemmygrad.ml 10 points 1 week ago

More than turning a profit, they could bend the arc of ai's climate crisis by competing in this domain of efficiency

32 gpus -> 1 gpu loosely translates to a 10x reduction in water and energy needed for interference after the 100x reduction in training requirements.

And these are just the improvements within 4 months...