cm0002@lemmy.world to Free Open-Source Artificial Intelligence@lemmy.worldEnglish · 3 days agoOpen Source DeepSeek R1 Runs at 200 Tokens Per Second on Raspberry Piwww.nextbigfuture.comexternal-linkmessage-square9fedilinkarrow-up132arrow-down12
arrow-up130arrow-down1external-linkOpen Source DeepSeek R1 Runs at 200 Tokens Per Second on Raspberry Piwww.nextbigfuture.comcm0002@lemmy.world to Free Open-Source Artificial Intelligence@lemmy.worldEnglish · 3 days agomessage-square9fedilink
minus-squareffhein@lemmy.worldlinkfedilinkEnglisharrow-up4·3 days agoYea… it’s not quite the same thing to actually run DeepSeek R1, a 671B model, and for example DeepSeek-R1-Distill-Qwen-1.5B
minus-squaresuokolinkfedilinkEnglisharrow-up2·3 days agoA recent i7 on CPU only can manage qwen 1.5 in a satisfactory way, comparable to big online players. Curious about recent ultra Intel and snapdragons
minus-squarehendrik@palaver.p3x.delinkfedilinkEnglisharrow-up1·3 days agoMy old computer and laptop run 13B models at 2 - 3 tokens a second on CPU only. That’s a bit slower than I can read. I wonder what my new phone does.
Yea… it’s not quite the same thing to actually run DeepSeek R1, a 671B model, and for example DeepSeek-R1-Distill-Qwen-1.5B
A recent i7 on CPU only can manage qwen 1.5 in a satisfactory way, comparable to big online players. Curious about recent ultra Intel and snapdragons
My old computer and laptop run 13B models at 2 - 3 tokens a second on CPU only. That’s a bit slower than I can read. I wonder what my new phone does.