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

<- View Parent
vintageballs@feddit.org ⁨2⁩ ⁨days⁩ ago

They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.

source
Sort:hotnewtop