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-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 · 2 months agomessage-square27linkfedilinkcross-posted to: technology@lemmygrad.mltechnology@lemmy.ml
minus-squarepppirate@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up1·2 months agobasically how fast the output speed is when it generates text
minus-squareLinktanklinkfedilinkarrow-up1·2 months 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.