@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-square25fedilinkarrow-up1141arrow-down10
arrow-up1141arrow-down1external-linkDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.com@misk@sopuli.xyz to Technology@beehaw.org • 1 month agomessage-square25fedilink
minus-square@morrowind@lemmy.mllinkfedilink5•edit-21 month agoThe hell is v3 32b. Are you talking about a distill
minus-square@vintageballs@feddit.orglinkfedilinkDeutsch1•1 month 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.