Now Available
NVIDIA GB300 NVL72 SYSTEMS
Rack-scale AI infrastructure with 72 Blackwell Ultra GPUs in a single liquid-cooled system. Built for
large-scale training, inference, and AI reasoning workloads.
OVERVIEW
RACK-SCALE AI INFRASTRUCTURE, NOT JUST SERVERS
The NVIDIA GB300 NVL72 is a different class of AI system. Rather than individual servers, it is a fully integrated, liquid-cooled rack that combines 72 Blackwell Ultra GPUs and 36 Grace CPUs into a single compute domain. The entire rack operates as one unified system, connected by fifth-generation NVLink, and is purpose-built for large-scale AI training, reasoning, and high-throughput inference.
Arc Compute offers GB300 NVL72 systems through leading OEM partners, with support for full rack deployments and large-scale infrastructure builds. Our team works with you from capacity planning through deployment to get these systems into production on your timeline.
AVAILABLE SYSTEMS
NVIDIA GB300 NVL72 SYSTEMS FROM LEADING OEM PARTNERS
Choose from validated GB300 NVL72 platforms designed for hyperscale AI deployments and high-density data center environments.
Supermicro GB300 NVL72
Now Available
- Fully integrated rack-scale AI system with direct liquid cooling
- Designed for large-scale AI training and inference workloads
- Optimized for rapid deployment of AI factory infrastructure
- Supports high-density data center environments
Aivres GB300 NVL72
Now Available
- High-density rack-scale system built for AI infrastructure at scale
- Direct liquid cooling for sustained, high-utilization operation
- Designed for large-scale model training and inference workload
- Built for hyperscale and enterprise AI environment
Planning a large-scale AI deployment?
Plan your GB300 infrastructurePLATFORM SPECS
NVIDIA GB300 NVL72 RACK-SCALE SYSTEM
The GB300 NVL72 is a fully integrated, liquid-cooled rack that operates as a single unified AI system. It combines 72 Blackwell Ultra GPUs with 36 Grace CPUs, connected by NVLink 5, to create one large compute domain capable of handling the most demanding AI workloads in production today.
Private AI Cloud
Dedicated GPU infrastructure with cloud-like flexibility. Built for startups that want to reduce cloud spend without giving up the on-demand experience their engineering teams are used to.
36 GRACE CPUS
36 NVIDIA Grace CPUs tightly integrated with the GPU fabric, purpose-built to minimize CPU-GPU bottlenecks in AI workloads.
NVLINK 5 INTERCONNECT
Dedicated GPU infrastructure with cloud-like flexibility. Built for startups that want to reduce cloud spend without giving up the on-demand experience their engineering teams are used to.
DIRECT LIQUID COOLING
Full rack liquid cooling designed for sustained, high-density operation. Required for the thermal envelope of 72 GPUs in a single rack.
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 GPU INFRASTRUCTURE
Tell us about your workloads, timeline, and deployment goals. Our team will help you evaluate GPU platforms, select the right architecture, and design infrastructure that fits your requirements.