NVL72 Achieves Up to 30x Better Throughput per MW than GB300 on AgentX Benchmark
nvidia · x · 2026-08-29
NVIDIA cites SemiAnalysis's AgentX benchmark to demonstrate the performance of its Vera Rubin NVL72 system.
In workloads simulating real-world agent runs, NVIDIA's internal tests show that Vera Rubin NVL72 achieves up to 30x better throughput per megawatt than the GB300 NVL72. The benchmark aims to measure AI infrastructure performance more accurately in agent scenarios.
More from Infra
- Scobleizer: Qwen Cloud is natively built around AI for better agent integration — Scobleizer · 2026-08-29
- a16z Partner: Only 2% of US Electricians Certified for DC Power — GregCook2011 · 2026-08-29
- The 'Boring' Network That Saves GPU Training Runs: OOB Management Explained — AccBalanced · 2026-08-29
- Running Generalist Robot Policies on STM32 and ESP32 Chips — yacineMTB · 2026-08-29
- Privacy architecture builds user trust to share sensitive health data with AI — bgmshana · 2026-08-29
- NVIDIA open-sources srt-slurm: YAML orchestration for inference on Slurm clusters — AccBalanced · 2026-08-29