Designed for AI Reasoning Performance
The NVIDIA GB300 NVL72 features a fully liquid-cooled, rack-scale design that unifies 72 NVIDIA Blackwell Ultra GPUs and 36 Arm®-based NVIDIA Grace™ CPUs in a single platform optimized for test-time scaling inference. AI factories powered with the GB300 NVL72 using NVIDIA Quantum-X800 InfiniBand or Spectrum™-X Ethernet paired with ConnectX®-8 SuperNICS provide a 50x higher output for reasoning model inference compared to the NVIDIA Hopper™ platform.
NVIDIA GB300 NVL72
- AI Reasoning Inference
- 288 GB of HBM3e
- NVIDIA Blackwell Architecture
- NVIDIA ConnectX-8 SuperNIC
- NVIDIA Grace CPU
- Fifth-Generation NVIDIA NVLink
About
Specification
Specifications
Configuration
72 NVIDIA Blackwell Ultra GPUs, 36 NVIDIA Grace CPUs
NVLink Bandwidth
130 TB/s
Fast Memory
Up to 40 TB
GPU Memory | Bandwidth
Up to 21 TB | Up to 576 TB/s
CPU Memory | Bandwidth
Up to 18 TB SOCAMM with LPDDR5X | Up to 14.3 TB/s
CPU Core Count
2,592 Arm Neoverse V2 cores
FP4 Tensor Core
1,400 | 1,100² PFLOPS
FP8/FP6 Tensor Core
720 PFLOPS
INT8 Tensor Core
23 PFLOPS
FP16/BF16 Tensor Core
360 PFLOPS
TF32 Tensor Core
180 PFLOPS
FP32
6 PFLOPS
FP64 / FP64 Tensor Core
100 TFLOPS
You May Also Like
Related products
-
NVIDIA T4
SKU: N/AMore Information- GPU Memory: 16 GB GDDR6
- CUDA Cores: 2560
- NVIDIA Tensor Cores: 320
- System Interface: x16 PCIe Gen3
-
NVIDIA DGX Spark GB10
SKU: N/AMore Information- Built on NVIDIA GB10 Grace Blackwell Superchip
- NVIDIA Blackwell GPU with fifth-generation Tensor Core technology
- NVIDIA Grace CPU with 20- core high-performance Arm architecture
- Up to 1 petaFLOP of AI performance using FP4
- 128 GB of coherent, unified system memory
- Support for up to 200 billion parameter model
- NVIDIA ConnectX™ networking to link two systems to work with models up to 405 billion parameters
- Up to 4 TB of NVMe storage
- Compact desktop form factor
-
NVIDIA DGX B300
SKU: N/AMore Information- Built with NVIDIA Blackwell Ultra GPUs
- 2.3TB of GPU memory space
- 72 petaFLOPS of training performance
- 144 petaFLOPS of inference performance
- NVIDIA networking
- Intel® Xeon® 6776P Processors
- Foundation of NVIDIA DGX BasePOD™ and NVIDIA DGX SuperPOD™
- Leverages NVIDIA AI Enterprise and NVIDIA Mission Control software
Our Customers
Previous
Next