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-squarepppirate@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up1·1 month agobasically how fast the output speed is when it generates text
minus-squareLinktanklinkfedilinkarrow-up1·1 month agoThank you! Seems like they could just put that more plainly in the headline instead of assuming everybody is an AI aficionado.
basically how fast the output speed is when it generates text
Thank you! Seems like they could just put that more plainly in the headline instead of assuming everybody is an AI aficionado.