while unified memory may offer better performance than unsoldered DDR system memory, it still won't be as great as 1.8TB/s bandwidth on high end consumer GPUs right now.
nvidias master plan may be making it the new normal to have "only" 400GB/s bandwidth, thus gatekeeping local model usage further behind "more memory but not as fast as the cloud can do it"
nvidias master plan may be making it the new normal to have "only" 400GB/s bandwidth, thus gatekeeping local model usage further behind "more memory but not as fast as the cloud can do it"