misk@sopuli.xyz to Technology@beehaw.org · 10 days agoDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square24fedilinkarrow-up1120
arrow-up1120external-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 · 10 days agomessage-square24fedilink
minus-squareSteevyT@beehaw.orglinkfedilinkarrow-up1·9 days agoHuh, yeah that actually is above my reading speed assuming 1 token = 1 word. Although, I found that anything above 100 words per minute, while slow to read, feels real time to me since that’s about the absolute top end of what most people type.
Huh, yeah that actually is above my reading speed assuming 1 token = 1 word. Although, I found that anything above 100 words per minute, while slow to read, feels real time to me since that’s about the absolute top end of what most people type.