COMING SOOn
NVIDIA VERA RUBIN NVL72 SYSTEMS
Next-generation rack-scale AI infrastructure with 72 Rubin Ultra GPUs and 36 Vera CPUs in a single liquid-cooled system. Designed for frontier-scale training, reasoning, and hyperscale inference.
Plan Your Vera Rubin NVL72 Deployment Explore Upcoming SystemsOVERVIEW
THE NEXT GENERATION OF
RACK-SCALE AI
The NVIDIA Vera Rubin NVL72 is the successor to the GB300 NVL72, combining 72 Rubin Ultra GPUs and 36 Vera CPUs into a single, unified rack-scale compute domain. Connected by next-generation NVLink, the entire system operates as one massive AI accelerator designed for the scale and complexity of frontier AI workloads. NVIDIA has stated the platform is designed to deliver significant gains in performance per watt and lower cost per token compared to previous generations, particularly for large-scale and mixture-of-experts models.
Arc Compute is working with Supermicro and Aivres to prepare Vera Rubin NVL72 systems for future deployment. While systems are not yet available for order, our team is actively supporting early infrastructure planning, facility design, and capacity forecasting for organizations building toward Rubin-generation rack-scale AI.
UPCOMING SYSTEMS
NVIDIA VERA RUBIN NVL72 SYSTEMS FROM SUPERMICRO AND AIVRES
Arc Compute is preparing to offer Vera Rubin NVL72 platforms from both OEM partners. System configurations, timelines, and availability will be announced as hardware becomes commercially available.
SUPERMICRO Vera Rubin NVL72
Now Available
- Rack-scale AI system built on the NVIDIA Vera Rubin NVL72 reference design
- Supermicro Data Center Building Block Solutions for end-to-end deployment
- Direct liquid cooling with Supermicro’s leading DLC technology
- Designed for hyperscale AI training, reasoning, and inference workloads
- View Supermicro Vera Rubin NVL72
Aivres Vera Rubin NVL72
Now Available
- Exascale AI rack based on the NVIDIA Vera Rubin NVL72 platform
- AI-native system design optimized for dense GPU deployments
- Full rack liquid cooling for sustained high-utilization operation
- Built for large-scale model training and production inference at scale
Planning next-generation AI infrastructure?
Plan your Vera Rubin NVL72 deploymentPLATFORM SPECS
NVIDIA VERA RUBIN NVL72
RACK-SCALE SYSTEM
The Vera Rubin NVL72 is a fully integrated, liquid-cooled rack designed to operate as a single unified AI system. It combines 72 Rubin Ultra GPUs with 36 Vera CPUs, connected by next-generation NVLink, and is built for the compute demands of frontier AI training, advanced reasoning, and hyperscale inference workloads.
72 RUBIN ULTRA GPUS
72 next-generation NVIDIA Rubin Ultra GPUs in a single rack, operating as one unified compute domain for frontier-scale AI workloads.
36 VERA CPUS
36 NVIDIA Vera CPUs purpose-built for tight integration with the GPU fabric, designed to minimize bottlenecks in AI and data-intensive workloads.
NEXT-GEN NVLINK
Next-generation NVLink interconnect providing high-bandwidth, low-latency connectivity across all 72 GPUs, enabling the full rack to operate as a single compute node.
LIQUID-COOLED ARCHITECTURE
Full rack liquid cooling designed for the thermal demands of 72 GPUs at sustained, high-density operation. Built for continuous AI factory workloads.
WHY ARC COMPUTE
THE TEAM BEHIND YOUR INFRASTRUCTURE
PURPOSE-BUILT INFRASTRUCTURE
Every deployment is designed around your specific workload, power, cooling, and facility requirements. No generic rack-and-ship configurations.
Trusted Across Industries
GET STARTED
PLAN YOUR NVIDIA VERA RUBIN NVL72 DEPLOYMENT
Tell us about your infrastructure goals and timeline. Our team can help you evaluate Vera Rubin NVL72 systems, design rack-scale infrastructure, and prepare your organization for next-generation AI deployments.