inari@piefed.zip to Technology@lemmy.worldEnglish · 29 天前I gave Qwen 3.8 27B a reverse-engineering job I assumed needed a frontier model, and it finished in 30 minuteswww.xda-developers.comexternal-linkmessage-square33linkfedilinkarrow-up1138arrow-down133
arrow-up1105arrow-down1external-linkI gave Qwen 3.8 27B a reverse-engineering job I assumed needed a frontier model, and it finished in 30 minuteswww.xda-developers.cominari@piefed.zip to Technology@lemmy.worldEnglish · 29 天前message-square33linkfedilink
minus-squarefrongt@lemmy.ziplinkfedilinkEnglisharrow-up7arrow-down3·29 天前Where do you think those models are trained? And most personal computing has tended towards only having a smartphone, and a laptop for a real PC. You can’t run much in the way of an LLM on those (at least not with any real speed).
minus-squarefloofloof@lemmy.calinkfedilinkEnglisharrow-up1arrow-down1·28 天前You can if the laptop is extremely expensive. But the laptop is extremely expensive.
Where do you think those models are trained?
And most personal computing has tended towards only having a smartphone, and a laptop for a real PC. You can’t run much in the way of an LLM on those (at least not with any real speed).
You can if the laptop is extremely expensive. But the laptop is extremely expensive.