NVIDIA Vera Rubin NVL72 page goes live: 72 Rubin GPUs, rack-scale agentic AI supercomputer
AIFlow_ML · x · 2026-10-28
NVIDIA's Vera Rubin NVL72 page is live: 72 Rubin GPUs plus 36 Vera CPUs per rack, with ConnectX-9 SuperNICs, BlueField-4 DPUs and NVLink 6 switching, pitched for agentic AI factories. NVIDIA claims training with one-fourth the GPUs and inference at one-tenth the cost per million tokens versus Blackwell, with full production ramping. Notably, HBM4 bandwidth specs on the page are lower than earlier GTC figures (see the bandwidth-cut analysis).
More from Infra
- fal.ai publicly hunting for B300/GB300 compute, 1MW+ chunks, delivery before year-end — isidentical · 2026-10-28
- EmbeddingGemma2 Turned Into a 20ms Real-Time Trainable Multimodal Endpoint on CPU — michellechen · 2026-10-28
- Seagate dips after 142% YTD surge, but AI-driven HDD boom keeps margins at records — TiernanRayTech · 2026-10-28
- NetBox Labs partnership targets AI factory config drift, chasing time-to-first-token — ai · 2026-10-28
- US holds 72% of world AI compute as EU's 5% share falls far below its 15% GDP weight — Jsevillamol · 2026-10-28
- Nvidia and Oracle to scale Vera Rubin NVL72 clusters on OCI to multi-gigawatt level — Beth_Kindig · 2026-10-28