GB300 NVL72
AI·HPC High-Performance GPU Cluster
Designed for AI inference performance and efficiency
Products
| |
GB300-NVL72 | NVIDIA GPU Solution for Ultra-Large AI Training·HPC Clusters
NVIDIA GPU
Ultimate GPU performance, complete AI infrastructure experience.
NVIDIA Preferred Partner XIIlab delivers.
NVIDIA Preferred Partner XIIlab delivers.
Select Product
Grace systems
NVIDIA's next-gen computing platform maximizing AI·HPC performance
GB300 NVL72
| GB300 NVL72 Technical Specifications | |
|---|---|
| Configuration | 72 NVIDIA Blackwell Ultra GPU, 36 NVIDIA Grace CPU |
| NVLink bandwidth | 130TB/s |
| NVLink memory bandwidth | Up to 40 TB |
| NVIDIA® NVSwitch™ | 4x |
| GPU memory bandwidth | 20 TB | Up to 576 TB/s |
| CPU memory bandwidth | 17 TB LPDDR5X | 14 TB/s |
| CPU Core | 2,592 ArmNeoverse V2 Core |
| FP4 Tensor Core | 1,400 | 1,100² FLOPS |
| FP8/FP6 Tensor Core | 720 FLOPS |
| INT8 Tensor Core | 23 FLOPS |
| FP16/BF16 Tensor Core | 360 FLOPS |
| TF32 Tensor Core | 180 FLOPS |
| FP32 | 6 FLOPS |
| FP64/FP64 Tensor Core | 2100 Tera FLOPS |
XIIlab
AI Professional Service
As an NVIDIA Preferred Partner, XIIlab provides end-to-end integrated technical support
for building and operating GPU infrastructure optimized for AI models and environments.
GPU Configuration Optimization
Workload-based hardware architecture design optimized for AI deployment from server delivery
AI Training & Inference Environment
Pre-configured AI workloads aligned with project goals and full lifecycle support
SW/HW Technical Support
Regular hardware monitoring and fault inspection system operated by dedicated AI engineers
NVIDIA DGX Platform Inquiry 
Email: sales@xiilab.com Contact: 02-2039-3145