☆ Yσɠƚԋσʂ ☆ to TechnologyEnglish · 9 个月前DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square14linkfedilinkarrow-up139arrow-down11cross-posted to: technology@lemmy.ml
arrow-up138arrow-down1external-linkDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.com☆ Yσɠƚԋσʂ ☆ to TechnologyEnglish · 9 个月前message-square14linkfedilinkcross-posted to: technology@lemmy.ml
minus-squarepinguinu [any]linkfedilinkarrow-up1·9 个月前You can use the smaller models on (beefy) consumer hardware already. That’s something, right? 😅
minus-squareCriticalResist8Alinkfedilinkarrow-up3·9 个月前I want the full 1TB model running on my 10 year old linux laptop
You can use the smaller models on (beefy) consumer hardware already. That’s something, right? 😅
I want the full 1TB model running on my 10 year old linux laptop
Just put your persistent memory as swap. Easy