NVIDIAEventDevelopersNovember 16, 2026

NVIDIA Vera Rubin debuts, sweeping MLPerf Training v6.1

Read original source →blogs.nvidia.com

Vera Rubin NVL72 hit the fastest time to train on six of seven MLPerf Training v6.1 benchmarks, up to 2x per-GPU performance over GB300 NVL72. In its first MLPerf Endpoints submission it claimed over 10x generational gains in throughput per watt for agentic AI.

3 sources

More stories today

Open the live feed