Tech Meridian ← LIVE FEED
PROMY MERIDIAN RU

NEWS · COMPANIES · #3675

NVIDIA Vera Rubin NVL72 leads MLPerf Endpoints v1.0 agentic inference with >10× throughput/kW vs GB300 (provisional)

Provisional MLPerf Endpoints v1.0 results show NVIDIA's Vera Rubin NVL72 delivering over 10× throughput per kilowatt versus the NVIDIA GB300 NVL72 at a shared minimum end-to-end interactivity of 50 tokens/sec per user; across Kimi K3, DeepSeek-V4.1-Flash and Qwen3.6-35B-A3B the Vera Rubin system achieves 5×–10× higher throughput/kW and 3×–5× higher end-to-end interactivity at matched concurrency. NVIDIA credits hardware (HBM4, Tensor Cores, 6th-gen NVLink) plus context-aware serving (prefix caching, state reuse, Dynamo routing) and model-specific kernels for the gains; the Vera Rubin results are provisional pending MLCommons verification.

KEY POINTS

  1. Provisional MLPerf Endpoints v1.0 results show NVIDIA's Vera Rubin NVL72 delivering over 10× throughput per kilowatt versus the NVIDIA GB300 NVL72 at a shared minimum end-to-end interactivity of 50 tokens/sec per user; across Kimi K3, DeepSeek-V4.1-Flash and Qwen3.6-35B-A3B the Vera Rubin system achieves 5×–10× higher throughput/kW and 3×–5× higher end-to-end interactivity at matched concurrency.
  2. NVIDIA credits hardware (HBM4, Tensor Cores, 6th-gen NVLink) plus context-aware serving (prefix caching, state reuse, Dynamo routing) and model-specific kernels for the gains; the Vera Rubin results are provisional pending MLCommons verification.
  3. If verified, the Vera Rubin NVL72’s much higher throughput per kilowatt could materially lower power costs and increase scalable, responsive agentic deployments for enterprises and cloud providers.

WHY IT MATTERS

If verified, the Vera Rubin NVL72’s much higher throughput per kilowatt could materially lower power costs and increase scalable, responsive agentic deployments for enterprises and cloud providers.

SOURCES & TIMELINE

1