RSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 1 month agoKimi-K3 Releases on HuggingFace 6/27huggingface.coexternal-linkmessage-square3linkfedilinkarrow-up15arrow-down10file-text
arrow-up15arrow-down1external-linkKimi-K3 Releases on HuggingFace 6/27huggingface.coRSS Bot@lemmy.bestiver.seMB to Hacker News@lemmy.bestiver.seEnglish · 1 month agomessage-square3linkfedilinkfile-text
minus-square9tr6gyp3@lemmy.worldlinkfedilinkEnglisharrow-up2·1 month ago3T model. Gonna need a data center to run this one.
minus-squarekibiz0r@midwest.sociallinkfedilinkEnglisharrow-up2·1 month agoOr two-three 768GB Mac Studios if Apple manages to get CXMT up to speed. Probably ~$50K. Not cheap, but an order of magnitude cheaper than a Blackwell stack.
3T model. Gonna need a data center to run this one.
Or two-three 768GB Mac Studios if Apple manages to get CXMT up to speed. Probably ~$50K. Not cheap, but an order of magnitude cheaper than a Blackwell stack.