Nvidia's Vera Rubin NVL72 Posts First MLPerf Inference Numbers, Claiming 3.7x Over Current Systems

Nvidia submitted its Vera Rubin NVL72 rack-scale system to MLPerf Inference v6.1, the industry benchmark run by MLCommons, and reported up to 3.7 times the throughput of the GB300 NVL72 on Qwen3-VL and up to 2.5 times on DeepSeek-R1, across the offline, server and interactive scenarios. The submissions ran vLLM together with Nvidia's Dynamo inference framework.

Two details matter more than the headline multiple. First, Vera Rubin entered the preview category, which MLPerf reserves for hardware that is not yet commercially available, so no independent buyer has reproduced the numbers on a purchased system. Second, the baseline is Nvidia's own prior generation rather than a competing accelerator, which measures generational progress and not competitive position.

The rest of the round is arguably the more durable signal. Nvidia says software optimization alone delivered up to 1.6 times higher performance over v6.0 on existing hardware, and a 288-graphics-processing-unit submission spanning four GB300 racks held 99 percent scaling efficiency against a single-rack baseline. MLCommons reported record participation for this round, and cloud providers submitted their own results, with Nebius claiming five first-place finishes across 20 category entries plus a Vera Rubin preview entry of its own.

For anyone modeling serving costs, the software gain is the figure to rely on today. It applies to installed fleets now, while the Vera Rubin figures describe a platform buyers cannot yet deploy.