From the source
NVIDIA's Vera Rubin NVL72 system made its MLPerf Inference v6.1 debut, delivering up to 3.7x higher throughput than GB300 NVL72 on Qwen3-VL and up to 2.5x higher throughput on
DeepSeek-R1.
- The GB300 NVL72 achieved 99% scaling efficiency across four racks with 288 GPUs.
- Software optimizations in v6.1 delivered up to 1.6x higher performance over v6.0.






