Vera Rubin NVL72 first benchmarks: up to 5.7x throughput per MW vs GB300
ArtificialAnlys · x · 2026-10-16
Artificial Analysis published the first AgentPerf results for NVIDIA's Vera Rubin NVL72, showing large per-megawatt throughput gains over its predecessor GB300 NVL72: 5.7x on DeepSeek V4 Pro, 5.4x on DeepSeek V4.1 Flash, 3.0x on GLM-5.2, and 2.8x on Kimi K3.
On DeepSeek V4.1 Flash, Vera Rubin serves 3.4x to 3.6x GB300's throughput per MW in the 230–350 tok/s per-user range, and reaches 906 tok/s per user with a single 4-GPU server — the fastest result on their leaderboard for any model.
Vera Rubin is Blackwell's successor; the NVL72 is a rack-scale system with 72 Rubin GPUs and 36 Vera CPUs.
Related event: Vera Rubin NVL72 hits 5.7x GB300 throughput per MW in first tests(3 posts)→
More from Infra
- TRL reproduces Modal's mixed-precision async RL: plain GRPO collapses, SC+MIS holds 0.72 — QGallouedec · 2026-10-16
- Hugging Face scales Indic pretraining with 2.8T tokens and an open data pipeline — Hugging Face Blog · 2026-10-16
- NVIDIA Vera Rubin NVL72 hits up to 5.7x GB300 throughput per MW on agent benchmark — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16
- Local AI is a routing problem, not a privacy feature: where each task should run — bigdata · 2026-10-16
- Moving agent work from GPUs to CPUs for durable, predictable actions — cramforce · 2026-10-16