MI355X has a lower cost per million tokens than the B200 at high throughput
Considering it’s an apples-to-apples comparison(8-GPU node) it’s quite reassuring for $AMD
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
MI355X has a lower cost per million tokens than the B200 at high throughput
Considering it’s an apples-to-apples comparison(8-GPU node) it’s quite reassuring for $AMD