Build your next
AI cluster on
NVIDIA Rubin.
8 Rubin GPUs. Direct liquid cooling.
A compact 2U platform from 2CRSi, with configuration choices shaped around your AI project.
8 GPUs
NVIDIA Rubin NVL8
2.3 TB
Total HBM4 GPU memory
2U
19-inch rack format
DLC
Direct liquid cooling
Plan the infrastructure
behind your next AI model.
01 / COMPUTE
Room for demanding models.
Bring eight Rubin GPUs and 2.3 TB of HBM4 memory into your AI infrastructure planning, from model development to inference.
02 / COOLING
Design density in from day one.
A fully liquid-cooled, 2U server puts cooling at the centre of the design. Discuss rack capacity and your facility’s liquid cooling requirements with 2CRSi.
03 / CONNECTIVITY
Think beyond a single node.
Sixth-generation NVLink connects GPUs within the platform. ConnectX-9 networking supports the conversation about your wider cluster architecture.
THE PLATFORM
Rubin acceleration.
The Godì 1.8 DLC combines NVIDIA HGX Rubin NVL8 with an x86 platform. Explore the system specification, then discuss the configuration your project needs.
GPU platform: NVIDIA HGX™ Rubin NVL8
Processors: Dual Intel® Xeon® 6
System memory: 32 DDR5 DIMM slots
Networking: 8 × ConnectX®-9 ports, 800 Gb/s
Storage bays: 8 × E1.S NVMe
LET'S SCOPE YOUR RUBIN PROJECT
Your workload.
Your constraints.
Your configuration.
Tell us what you’re planning. Start a conversation with 2CRSi about a Rubin-based infrastructure that fits your project.
01. Review your workload and deployment goals.
02. Discuss compute, networking and cooling requirements.
03. Clarify configuration options and availability.
Request your Rubin configuration
Attention: NVIDIA Rubin GPUs are under embargo from the United States Department of Commerce towards multiple countries across the world. 2CRSi group and all its subsidiaries are following US trade legislation and will ensure through compliance process is complete before all shipments of its GPU systems. Feel free to ask any question regarding the compliance process to your 2CRSi Sales agent or contacting the U.S. Department of Commerce.
SCALE YOUR INFRASTRUCTURE
From a single server
to a complete AI
rack.
Bring Godì Rubin servers into a fully integrated, liquid-cooled rack. Plan compute, networking, power and cooling together, with a configuration built around your deployment.
NVIDIA Rubin GPUs, up to: 72
2U DLC GPU servers: 9
19-inch rack: 48U
- An integrated foundation for AI at scale.
Combine servers with validated InfiniBand or Ethernet switch configurations and 2+2 redundant power shelves.
- Cooling designed around your facility.
Discuss in-row liquid-to-liquid CDUs, fluid networks and connection to your facility’s cooling infrastructure.
- Visibility across power and cooling.
Integrated management supports real-time cluster monitoring, with Modbus, Redfish and REST interfaces.
What are you building next?
Bring your use case to the discussion. We’ll help you assess the platform against your requirements.
AI development
Training & fine-tuning
Discuss model size, GPU memory needs and how your training environment should grow.
AI services
Inference infrastructure
Define your priorities for model serving, from concurrency and latency to deployment scale.
Research & engineering
Accelerated computing
Explore GPU infrastructure for your scientific workloads and data-intensive applications.