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
- Magnitude open-source inference engine beats Ollama by over 2x with auto-tuned kernels — nickbaumann_ · 2026-10-15
- Nvidia to announce $28B in AI investments in Europe this week, report says — georgemillo · 2026-10-15
- A $10,811 Cloudflare Bill From an Unused AI-Written Test Project: Refunds Aren't a Safety Net — sujingshen · 2026-10-15
- Retraining-Free Method Turns Transformers Into Elastic Models Adapting to Any Compute Budget — VISLab-Amsterdam · 2026-10-15
- vLLM's MTP3 validation: AIME25 up to 0.9667, prefill kernels up to 84% lower latency — vllm_project · 2026-10-15
- Open-weights s1-llm-auto-router picks the right LLM in 26ms on a CPU — airesearch12 · 2026-10-15