BeefAndPoultry@lemmus.org to LocalLLaMA@sh.itjust.worksEnglish · 8 days agoinclusionAI/Ling-3.1-flash 560b-a25bhuggingface.coexternal-linkmessage-square2linkfedilinkarrow-up111arrow-down12
arrow-up19arrow-down1external-linkinclusionAI/Ling-3.1-flash 560b-a25bhuggingface.coBeefAndPoultry@lemmus.org to LocalLLaMA@sh.itjust.worksEnglish · 8 days agomessage-square2linkfedilink
minus-squarelibrekitty@lemmy.todaylinkfedilinkEnglisharrow-up4·7 days ago“flash” -> looks inside -> over 200B parameters i mean i’m sure it’s much smaller than the non flash version, but my hope dies pretty quick when i realize i need a datacenter to run a model
minus-squareSchilling2304@thelemmy.clublinkfedilinkEnglisharrow-up2·2 days agoFor real… Flash used to mean small enough for like a very high end consumer GPU lmao
“flash” -> looks inside -> over 200B parameters
i mean i’m sure it’s much smaller than the non flash version, but my hope dies pretty quick when i realize i need a datacenter to run a model
For real… Flash used to mean small enough for like a very high end consumer GPU lmao