Avieshek@lemmy.world to Technology@lemmy.worldEnglish · 11 days agoEdward Snowden slams Nvidia's RTX 50-series 'F-tier value,' whistleblows on lackluster VRAM capacitywww.tomshardware.comexternal-linkmessage-square101fedilinkarrow-up1373arrow-down195
arrow-up1278arrow-down1external-linkEdward Snowden slams Nvidia's RTX 50-series 'F-tier value,' whistleblows on lackluster VRAM capacitywww.tomshardware.comAvieshek@lemmy.world to Technology@lemmy.worldEnglish · 11 days agomessage-square101fedilink
minus-squareTeamAssimilation@infosec.publinkfedilinkEnglisharrow-up389·11 days agoEdward Snowden doing GPU reviews? This timeline is becoming weirder every day.
minus-squareWinged_Hussar@lemmy.worldlinkfedilinkEnglisharrow-up90·11 days agoLegitimately thought this was a hard-drive.net post
minus-squareGamingChairModel@lemmy.worldlinkfedilinkEnglisharrow-up55·11 days ago“Whistleblows” as if he’s some kind of NVIDIA insider.
minus-square0x0@programming.devlinkfedilinkEnglisharrow-up1·10 days agoIntel Insider now that would’ve made for great whistleblowing headlines.
minus-squareEager Eagle@lemmy.worldlinkfedilinkEnglisharrow-up48·11 days agoI bet he just wants a card to self host models and not give companies his data, but the amount of vram is indeed ridiculous.
minus-squareJeena@piefed.jeena.netlinkfedilinkEnglisharrow-up25·11 days agoExactly, I’m in the same situation now and the 8GB in those cheaper cards don’t even let you run a 13B model. I’m trying to research if I can run a 13B one on a 3060 with 12 GB.
minus-squareThe Hobbyist@lemmy.ziplinkfedilinkEnglisharrow-up15·11 days agoYou can. I’m running a 14B deepseek model on mine. It achieves 28 t/s.
minus-squareJeena@piefed.jeena.netlinkfedilinkEnglisharrow-up6·11 days agoOh nice, that’s faster than I imagined.
minus-squarelevzzz@lemmy.worldlinkfedilinkEnglisharrow-up4·11 days agoYou need a pretty large context window to fit all the reasoning, ollama forces 2048 by default and more uses more memory
minus-squaremanicdave@feddit.uklinkfedilinkEnglisharrow-up4·11 days agoI’m running deepseek-r1:14b on a 12GB rx6700. It just about fits in memory and is pretty fast.
minus-squaresecret300@lemmy.sdf.orglinkfedilinkEnglisharrow-up11·11 days agoSwear next he’s gonna review hentai games Oh wait… https://www.youtube.com/watch?v=fAf1Syz17JE
minus-squarenewcockroach@lemmy.worldlinkfedilinkEnglisharrow-up8·10 days ago“Some hentai games are good” -Edward Snowden
minus-squareඞmir@lemmy.mllinkfedilinkEnglisharrow-up9·11 days agoI’ll keep believing this is a theonion post
minus-squareSimulation6@sopuli.xyzlinkfedilinkEnglisharrow-up1·10 days agoDoes he work for Nvidia? Seems out of character for him.
Edward Snowden doing GPU reviews? This timeline is becoming weirder every day.
Legitimately thought this was a hard-drive.net post
“Whistleblows” as if he’s some kind of NVIDIA insider.
Intel Insider now that would’ve made for great whistleblowing headlines.
I bet he just wants a card to self host models and not give companies his data, but the amount of vram is indeed ridiculous.
Exactly, I’m in the same situation now and the 8GB in those cheaper cards don’t even let you run a 13B model. I’m trying to research if I can run a 13B one on a 3060 with 12 GB.
You can. I’m running a 14B deepseek model on mine. It achieves 28 t/s.
Oh nice, that’s faster than I imagined.
You need a pretty large context window to fit all the reasoning, ollama forces 2048 by default and more uses more memory
I’m running deepseek-r1:14b on a 12GB rx6700. It just about fits in memory and is pretty fast.
Swear next he’s gonna review hentai games
Oh wait… https://www.youtube.com/watch?v=fAf1Syz17JE
“Some hentai games are good” -Edward Snowden
Note that this is from 2003
I’ll keep believing this is a theonion post
Does he work for Nvidia? Seems out of character for him.