On GLM-5.2/5.3, MI355X lands between Hopper and Blackwell. At 100 tok/s per user it serves ~26M tokens/s per MW, ahead of H200 (~16M) but behind B200 (~42M) and B300 (~44M), and its single-agent speed matches H200 at 228 tok/s, against 312 on B200 and 333 on B300.
AMD MI355X lands between Hopper and Blackwell on GLM serving
AISummary
Artificial Analysis says AMD's MI355X serves about 26M tokens/s per MW at 100 tok/s per user on GLM-5.2/5.3. That beats H200 at about 16M but trails B200 at about 42M and B300 at about 44M. Single-agent speed is 228 tok/s, matching H200 and below B200 at 312 and B300 at 333.
Post on XView on X
Source: Artificial Analysis · x.comPublished · added here