☆ Yσɠƚԋσʂ ☆ to

TechnologyEnglish · 9 months ago

DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI

venturebeat.com

cross-posted to:
technology@lemmy.ml

38

DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI

venturebeat.com

☆ Yσɠƚԋσʂ ☆ to

TechnologyEnglish · 9 months ago

cross-posted to:
technology@lemmy.ml

DeepSeek's free 685B-parameter AI model runs at 20 tokens/second on Apple's Mac Studio, outperforming Claude Sonnet while using just 200 watts, challenging OpenAI's cloud-dependent business model.

Chat

CriticalResist8A
link
fedilink
arrow-up
3·
8 months ago
I want the full 1TB model running on my 10 year old linux laptop
- pinguinu [any]
  link
  fedilink
  arrow-up
  2·
  8 months ago
  Just put your persistent memory as swap. Easy