misk@sopuli.xyz to Technology@beehaw.org · 2 months agoDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square25fedilinkarrow-up1140arrow-down10cross-posted to: technology@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 · 2 months agomessage-square25fedilinkcross-posted to: technology@lemmy.ml
minus-squaremorrowind@lemmy.mllinkfedilinkarrow-up5·edit-22 months agoThe he’ll is v3 32b. Are you talking about a distill
minus-squarevintageballs@feddit.orglinkfedilinkDeutscharrow-up1·2 months agoThey probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.
The he’ll 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.