cantankerous_cashew@lemmy.world to Apple@lemmy.world · 16 days agoMac Studio With M3 Ultra Runs Massive DeepSeek R1 AI Model Locallywww.macrumors.comexternal-linkmessage-square4fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkMac Studio With M3 Ultra Runs Massive DeepSeek R1 AI Model Locallywww.macrumors.comcantankerous_cashew@lemmy.world to Apple@lemmy.world · 16 days agomessage-square4fedilink
minus-squareJohn Richard@lemmy.worldlinkfedilinkEnglisharrow-up0·16 days agoIt would be less if NVIDIA & AMD wasn’t in an antitrust duopoly. You can get two XTX for less than $2000 with 48GB total VRAM.
minus-squarevanderbilt@lemmy.worldlinkfedilinkarrow-up0·15 days agoUnfortunately getting an AI workload to run on those XTXs, and run correctly, is another story entirely.
minus-squareJohn Richard@lemmy.worldlinkfedilinkEnglisharrow-up0·edit-215 days agoROCm has made a lot of improvements. $2000 for 48GB of VRAM makes up for any minor performance decrease as opposed to spending $2200 or more for 24GB VRAM with NVIDIA.
It would be less if NVIDIA & AMD wasn’t in an antitrust duopoly. You can get two XTX for less than $2000 with 48GB total VRAM.
Unfortunately getting an AI workload to run on those XTXs, and run correctly, is another story entirely.
ROCm has made a lot of improvements. $2000 for 48GB of VRAM makes up for any minor performance decrease as opposed to spending $2200 or more for 24GB VRAM with NVIDIA.