MLPerf® Inference v6.1 Per-GPU Results: The 5.7× Headline, Recomputed for Hardware You Can Buy
Per-GPU recomputation of MLPerf® Inference v6.1: the 5.7× headline is 3.04× for Available hardware, and software moved AMD 37.9%.
gpt-oss-120b
Per-GPU recomputation of MLPerf® Inference v6.1: the 5.7× headline is 3.04× for Available hardware, and software moved AMD 37.9%.