xs83·قبل 9 أشهر·discussIf you mean CUDA specific then yes. The biggest benefit of these machines over the others is the CUDA ecosystem and tools like cuDF, cuGraph etc
xs83·قبل 9 أشهر·discussTTFT on a Mac is terrible and only increases as the context increases, thats why many are selling their M3 Ultra 512GB
xs83·قبل 9 أشهر·discussNow this looks much more interesting! Is the top one input tokens and the second one output tokens?So 38.54 t/s on 120B? Have you tested filling the context too?