@misk@sopuli.xyz to Technology@beehaw.org • 26 days agoDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square24fedilinkarrow-up1110cross-posted to: technology@lemmy.ml
arrow-up1110external-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 • 26 days agomessage-square24fedilinkcross-posted to: technology@lemmy.ml
minus-square@morrowind@lemmy.mllinkfedilink2•edit-225 days agoThe he’ll is v3 32b. Are you talking about a distill
minus-square@vintageballs@feddit.orglinkfedilinkDeutsch1•20 days 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.