NVIDIA Vera Rubin NVL72 Tops Its Debut MLPerf Inference v6.1 Round, Reaching 3.7x GB300 NVL72 Throughput
In its first MLPerf Inference preview submission, published September 16 with v6.1, Vera Rubin NVL72 hits up to 3.7x GB300 NVL72 throughput on Qwen3-VL, while a 288-GPU GB300 run posts 99% scaling efficiency.