minus-squareIndeterminateName@beehaw.orgtoTechnology@beehaw.org•DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIlinkfedilinkarrow-up27·10 days agoA bit like a syllable when you are talking about text based responses. 20 tokens a second is faster than most people could read the output so that’s sufficient for a real time feeling “chat”. linkfedilink
A bit like a syllable when you are talking about text based responses. 20 tokens a second is faster than most people could read the output so that’s sufficient for a real time feeling “chat”.