US EditionSupermicro Reveals DCBBS® with New NVIDIA Vera Rubin NVL72, HGX Rubin NVL8, and Vera CPU Systems, Designed to Accelerate Customer Time-to-Market
Supermicro’s new AI systems deliver up to 10 times better throughput per watt and reduce token cost by 90%, using advanced liquid-cooling for efficient large-scale AI workloads.
- On March 16, 2026, Super Micro Computer, Inc. unveiled NVIDIA Vera Rubin NVL72, HGX Rubin NVL8 and Vera CPU systems built on its Data Center Building Block Solutions, previewed at GTC San Jose 2026.
- To meet Vera Rubin's thermal and power needs, Supermicro engineered DCBBS with in-rack CDU, in-row CDU, manifolds, and an optional Liquid-to-Air sidecar, enabling rapid Rubin platform deployments.
- The NVL72 combines six co-designed chips to deliver up to 3.6 Exaflops inference, 75TB memory, and 1.6 PB/s HBM4 while supporting 72 Rubin GPUs per rack and targeting 10x throughput per watt versus Blackwell.
- Manufacturing across the US, Taiwan, and the Netherlands supports near-term availability, with Supermicro experts discussing procurement at booth #1113.
- Charles Liang, president and CEO of Supermicro, framed the portfolio as part of a new era where AI factories are essential, with DCBBS enabling large-scale deployments on MGX rack architecture.
24 Articles
24 Articles
Supermicro Reveals DCBBS® with New NVIDIA Vera Rubin NVL72, HGX Rubin NVL8, and Vera CPU Systems, Designed to Accelerate Customer Time-to-Market - The Tribune
San Jose (California) [US], March 17: Super Micro Computer, Inc. (NASDAQ: SMCI), a Total IT Solution Provider for Cloud Computing, AI/ML, Storage, and 5G/Edge, today unveiled its upcoming system portfolio powered by the NVIDIA Vera Rubin platform. As data centers transform into AI factories, producing intelligence at massive scale, agentic reasoning, long-context AI, and Mixture-of-Experts (MoE) workloads are driving demand for an entirely new c…
Aspen Daily News
Supermicro Reveals DCBBS® with New NVIDIA Vera Rubin NVL72, HGX Rubin NVL8, and Vera CPU Systems, Designed to Accelerate Customer Time-to-Market
Supermicro's NVIDIA Vera Rubin NVL72 and HGX Rubin NVL8 systems are built on the DCBBS liquid-cooling stack, targeting up to 10x throughput per watt and one-tenth the token cost, compared to NVIDIA Blackwell solutions.Supermicro's 2U HGX Rubin NVL8 system is…
Advert: Red Hat's open hybrid cloud Intel Xeon is used as a host CPU, underlining its role in orchestrating, scaling and protecting the modern infrastructure of AI. News: In NVIDIA GTC 2026, Intel announced that Intel Xeon 6 is being used as host processor for NVIDIA Rubin NVL8 systems. This highlights Xeon's role in providing architectural continuity and scalability for GPU-accelerated AI systems as workloads are oriented towards massive and re…
Supermicro Reveals DCBBS with New NVIDIA Vera Rubin NVL72, HGX Rubin NVL8, and Vera CPU Systems
Super Micro Computer, Inc. (NASDAQ: SMCI), a Total IT Solution Provider for Cloud Computing, AI/ML, Storage, and 5G/Edge, today unveiled its upcoming system portfolio powered by the NVIDIA Vera Rubin platform. As data centers transform into AI factories, producing intelligence at massive scale, agentic reasoning, long-context AI, and Mixture-of-Experts (MoE) workloads are driving demand for an entirely new class of compute and storage infrastruc…
Coverage Details
Bias Distribution
- 64% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
