JOMusic@lemmy.ml to Technology@lemmy.worldEnglish · 2 days agoUS Bill proposed to jail people who download Deepseekwww.404media.coexternal-linkmessage-square131fedilinkarrow-up1760arrow-down115cross-posted to: nottheonion@lemmy.worldopensource@lemmy.mlpolitics@lemmy.worldusa@lemmy.ml
arrow-up1745arrow-down1external-linkUS Bill proposed to jail people who download Deepseekwww.404media.coJOMusic@lemmy.ml to Technology@lemmy.worldEnglish · 2 days agomessage-square131fedilinkcross-posted to: nottheonion@lemmy.worldopensource@lemmy.mlpolitics@lemmy.worldusa@lemmy.ml
minus-squareKnock_Knock_Lemmy_In@lemmy.worldlinkfedilinkEnglisharrow-up2·17 hours 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-squareKyuuketsuki@lemmy.mllinkfedilinkEnglisharrow-up1·14 hours 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.
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.