NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut
Source
Zhihan Jiang
Author
Zhihan Jiang
Date
Terms in this piece · Glossary
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Why it matters
Concrete benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → data shows Vera Rubin NVL72 delivering 3.7x the throughput of GB300 NVL72 and near-linear scaling across racks, numbers that matter for anyone forecasting inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition → cost and capacity.
articleVera Rubin NVL72 vs GB200 NVL72? Inference TCO & Architecture AnalysisAlec Ibarra
articleVera Rubin NVL72 Agentic Inference: 67x better Performance per DollarBryan Shan
articleHow NVIDIA Groq 3 LPX Deterministic Execution Drives Power-Efficient High-Interactivity Inference on NVIDIA Vera RubinTanya Lenz