NVIDIA GB200 NVL4 liquid-cooled MGX platform with 4 Blackwell GPUs and 2 Grace CPUs over NVLink-C2C for scientific computing, AI for science, training, and inference.
Fast Shipping
100k+ SKUs
8/5 Support
Certified
NVIDIA GB200 NVL4 | Grace Blackwell HPC and AI Platform
NVIDIA GB200 NVL4 Grace Blackwell Platform (GB200-NVL4)
NVIDIA GB200 NVL4 is a Grace Blackwell platform for converged HPC and AI workloads. It connects four Blackwell GPUs with two Grace CPUs using NVLink and NVLink-C2C and is designed for compatible liquid-cooled NVIDIA MGX modular servers.
Availability / RFQ: This product is a current NVIDIA platform or component and is listed for RFQ. Pricing, allocation, quantity, configuration, support, and lead time can vary with current channel conditions. Contact Catalyst Data Solutions to discuss current status, compatibility, configuration requirements, and sourcing options.
End-user / export compliance notice: Advanced AI accelerators and systems may be subject to applicable U.S. export controls, end-user/end-use restrictions, destination requirements, and OEM/channel policies. Catalyst may request purchaser, final end-user, intended-use, and deployment-location information before a quote or fulfillment can be approved. An RFQ does not guarantee allocation or shipment.
Technical Specifications
| SKU | GB200-NVL4 |
|---|---|
| Product Type | Grace Blackwell HPC / AI Platform |
| GPU Configuration | 4x NVIDIA Blackwell GPUs |
| CPU Configuration | 2x NVIDIA Grace CPUs |
| CPU-GPU Interconnect | NVIDIA NVLink-C2C |
| GPU Scale-Up | Fifth-generation NVIDIA NVLink bridge |
| System Platform | Liquid-cooled NVIDIA MGX modular servers |
| Primary Focus | Scientific computing and AI for science |
| Availability Status | Available / RFQ |
Deployment and Compatibility Considerations
- Use a validated liquid-cooled MGX/OEM server designed for GB200 NVL4.
- Confirm rack power, liquid loop, CDU, manifold, and server thermal requirements.
- Choose scale-out networking and storage for the target scientific or AI workload.
- Validate CUDA-X, HPC libraries, scheduler, MPI, and application certification.
Common Use Cases
- Scientific simulation
- AI for science training and inference
- Engineering and computational workloads
- HPC clusters with tightly coupled CPU-GPU compute
Frequently Paired Infrastructure
- Liquid-cooled MGX systems
- ConnectX networking
- Quantum InfiniBand or Spectrum-X Ethernet
- Parallel AI/HPC storage
- Rack cooling and power infrastructure
Official NVIDIA Documentation
Frequently Asked Questions
What is the GB200 NVL4 processor configuration?
NVIDIA describes GB200 NVL4 as four Blackwell GPUs paired with two Grace CPUs over NVLink-C2C.
What type of server does GB200 NVL4 use?
NVIDIA positions GB200 NVL4 for compatible liquid-cooled MGX modular servers.
| product type | HPC / AI Compute Platform |
|---|---|
| Architecture / Series | NVIDIA Grace Blackwell GB200 NVL4 |
| Accelerator Configuration | 4 Blackwell GPUs / 2 Grace CPUs |
| Cooling Type | Liquid-Cooled MGX Platform |
| Availability Status | Available / RFQ |
