Learn about this first
NVIDIA's measurements show that, for agent workloads, Vera Rubin NVL72 delivers up to 30 times the throughput per megawatt of GB300 NVL72 and reduces the cost per million tokens by a factor of 35.
Latest developments
NVIDIA Vera Rubin NVL72 Sets a New Standard for AI Agent Efficiency: Up to 30 Times More Work per Watt
Event progress1
NVIDIA releases benchmark results for Vera Rubin NVL72
NVIDIA Blog: NVIDIA Vera Rubin NVL72 sets a new standard for AI agent efficiency: work per watt increased by up to 30×