The Frontier · Tags

#qwen3-vl

1 published article

• Compute & power · The Stack

  Vera Rubin NVL72's first MLPerf Inference v6.1 numbers: up to 3.7x vs GB300 on Qwen3-VL

  NVIDIA's 16 September 2026 preview submission puts Vera Rubin NVL72 on DeepSeek-R1 and Qwen3-VL. Distinct from the earlier Vera Rubin production dispatch: this is the benchmark stack.