Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Nvidia releases new AI chip with 480GB CPU RAM, 96GB GPU RAM. Parent comment
A more appropriate comparison is the fp16 performance.
It seems to be 27 tflops for the 38 core M2, and 330 for the 4090.
The more useful for training fp16 with fp32 accumulate is 165 for the 4090, I don't know about the apple one.
There are no comments on this comment yet.
A more appropriate comparison is the fp16 performance.
It seems to be 27 tflops for the 38 core M2, and 330 for the 4090.
The more useful for training fp16 with fp32 accumulate is 165 for the 4090, I don't know about the apple one.