inari@piefed.zip to Technology@lemmy.worldEnglish · 3 months agoI 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-square7linkfedilinkarrow-up10arrow-down10
arrow-up10arrow-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 · 3 months agomessage-square7linkfedilink
minus-squarelnxtx (xe/xem/xyr)@sopuli.xyzlinkfedilinkEnglisharrow-up0·3 months agoNice, but I want lower prices for the RAM and SSD modules.
minus-squarePlasticExistence@lemmy.worldlinkfedilinkEnglisharrow-up0·3 months agoI agree, but this will help pop the bubble because local models we can run on our own hardware will crash the demand for data centers
minus-squarefrongt@lemmy.ziplinkfedilinkEnglisharrow-up0arrow-down1·3 months agoWhere 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).
Nice, but I want lower prices for the RAM and SSD modules.
I agree, but this will help pop the bubble because local models we can run on our own hardware will crash the demand for data centers
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).