misk@sopuli.xyz to Technology@beehaw.org · 1 month agoDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square27linkfedilinkarrow-up1141arrow-down10cross-posted to: technology@lemmygrad.mltechnology@lemmy.ml
arrow-up1141arrow-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 · 1 month agomessage-square27linkfedilinkcross-posted to: technology@lemmygrad.mltechnology@lemmy.ml
minus-squaremorrowind@lemmy.mllinkfedilinkarrow-up5·edit-21 month agoThe hell is v3 32b. Are you talking about a distill
minus-squarevintageballs@feddit.orglinkfedilinkDeutscharrow-up1·28 days agoThey probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.
The hell is v3 32b. Are you talking about a distill
They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.