misk@sopuli.xyz to Technology@beehaw.org · 9 days agoDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square27fedilinkarrow-up1140arrow-down10cross-posted to: technology@lemmygrad.mltechnology@lemmy.ml
arrow-up1140arrow-down1external-linkDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.commisk@sopuli.xyz to Technology@beehaw.org · 9 days agomessage-square27fedilinkcross-posted to: technology@lemmygrad.mltechnology@lemmy.ml
minus-squarevintageballs@feddit.orglinkfedilinkDeutscharrow-up1·4 days agoThey probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.
They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.