sabreW4K3 to Tech@programming.dev · 4 months agoThe first GPT-4-class AI model anyone can download has arrived: Llama 405Barstechnica.comexternal-linkmessage-square10fedilinkarrow-up167arrow-down14cross-posted to: [email protected]
arrow-up163arrow-down1external-linkThe first GPT-4-class AI model anyone can download has arrived: Llama 405Barstechnica.comsabreW4K3 to Tech@programming.dev · 4 months agomessage-square10fedilinkcross-posted to: [email protected]
minus-squarexionzui@sh.itjust.workslinkfedilinkarrow-up9·edit-24 months agoYou can get usable performance on a CPU with good memory bandwidth. Apple studios are the best way to get that right now, but a good Epyc with 256GB of RAM works too. Of course, you could also just run 5 GPUs
minus-squareIsThisAnAI@lemmy.worldlinkfedilinkarrow-up5arrow-down1·4 months ago“usable” sure if you want to wait 10 minutes a word.
You can get usable performance on a CPU with good memory bandwidth. Apple studios are the best way to get that right now, but a good Epyc with 256GB of RAM works too.
Of course, you could also just run 5 GPUs
“usable” sure if you want to wait 10 minutes a word.