JOMusic@lemmy.ml to Technology@lemmy.worldEnglish · 1 year agoUS Bill proposed to jail people who download Deepseekwww.404media.coexternal-linkmessage-square132fedilinkarrow-up1815arrow-down116cross-posted to: nottheonion@lemmy.worldhackernewspolitics@lemmy.world
arrow-up1799arrow-down1external-linkUS Bill proposed to jail people who download Deepseekwww.404media.coJOMusic@lemmy.ml to Technology@lemmy.worldEnglish · 1 year agomessage-square132fedilinkcross-posted to: nottheonion@lemmy.worldhackernewspolitics@lemmy.world
minus-squareKnock_Knock_Lemmy_In@lemmy.worldlinkfedilinkEnglisharrow-up2·1 year agoIt’s easy to run a distilled version of the R1 model locally. It’s very difficult to run the full version. Min $6k to get 7 tokens per second.
minus-squarerumba@lemmy.ziplinkfedilinkEnglisharrow-up2·edit-21 year agoHere’s one for 2k if you don’t mine jank (edit: and 3-4 tokens :) ) https://digitalspaceport.com/how-to-run-deepseek-r1-671b-fully-locally-on-2000-epyc-rig/
minus-squareKyuuketsuki@lemmy.mllinkfedilinkEnglisharrow-up1·1 year agoI hear its easy, but I’ve had no luck at all on the most distilled models (for prelim testing), and am wondering how things have broken so badly.
It’s easy to run a distilled version of the R1 model locally. It’s very difficult to run the full version. Min $6k to get 7 tokens per second.
Here’s one for 2k if you don’t mine jank (edit: and 3-4 tokens :) )
https://digitalspaceport.com/how-to-run-deepseek-r1-671b-fully-locally-on-2000-epyc-rig/
I hear its easy, but I’ve had no luck at all on the most distilled models (for prelim testing), and am wondering how things have broken so badly.