this post was submitted on 25 Mar 2025

38 points (97.5% liked)

Technology

1089 readers

44 users here now

A tech news sub for communists

founded 2 years ago

MODERATORS

[email protected]

38

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 [email protected] to c/[email protected]

15 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 3 points 6 days ago (1 children)

I want the full 1TB model running on my 10 year old linux laptop

[–] [email protected] 2 points 6 days ago

Just put your persistent memory as swap. Easy