The NVIDIA GB200 NVL72 is a liquid-cooled, rack-scale solution that connects 36 Grace CPUs and 72 Blackwell GPUs to function as a single, massive GPU. Designed for the most demanding trillion-parameter LLM training and real-time inference workloads, it delivers up to 1.4 exaflops of AI performance.
- 72 NVIDIA Blackwell GPUs and 36 NVIDIA Grace CPUs in a single rack configuration.
- Fifth-generation NVLink interconnect providing 130TB/s aggregate bandwidth.
- Liquid-cooled design for maximum energy efficiency and compute density.
- Delivers 30x faster real-time LLM inference compared to previous generation H100 systems.
- Integrated BlueField-3 DPUs for accelerated networking, storage, and security.
- Support for NVIDIA Quantum-X800 InfiniBand and Spectrum-X800 Ethernet.
- Unified memory architecture across CPUs and GPUs for complex data processing.
- Redundant power supplies and cooling manifolds for enterprise-grade reliability.
- Scalable architecture for multi-rack deployments in hyperscale data centers.
NVIDIA
NVIDIA - GB200 NVL72 Platform - Blackwell AI Rack-Scale Platform
For a quote, contact us at info@tropical.com
- SKU:
- GB200 NVL72 Platform
- Weight:
- 3,000.00 LBS
- Width:
- 24.00 (in)
- Height:
- 79.00 (in)
- Depth:
- 48.00 (in)
Related Products
A relatable product
SuperMicro
Supermicro - NVIDIA GB200 NVL72 - Rack-Scale AI Supercomputer
The Supermicro NVIDIA GB200 NVL72 is a liquid-cooled, rack-scale AI supercomputer designed for the most demanding generative AI and LLM training workloads. It integrates 72 Blackwell GPUs and 36...
NVIDIA
NVIDIA - GB200 Superchip Platform - Blackwell Architecture AI Computing Node
The NVIDIA GB200 Grace Blackwell Superchip is a revolutionary processor designed for trillion-parameter scale generative AI and high-performance computing. It integrates two NVIDIA Blackwell GPUs and...
NVIDIA - DGX GB200 NVL72 - Rack-Scale Liquid-Cooled AI Supercomputer
The NVIDIA GB200 NVL72 is a rack-scale, liquid-cooled exascale computer designed for real-time trillion-parameter large language model (LLM) inference and massive-scale AI training. It integrates 36...
NVIDIA
NVIDIA - GB200 - Grace Blackwell Enterprise AI Superchip
The NVIDIA GB200 Grace Blackwell Superchip is a premier AI module engineered for the most demanding trillion-parameter large language model (LLM) workloads. It combines the power of the NVIDIA Grace...
NVIDIA - DGX B200 - Blackwell AI Infrastructure Platform
The NVIDIA DGX B200 is a unified AI platform designed for the entire develop-to-deploy pipeline, providing a foundation for enterprise AI factories. Built on the NVIDIA Blackwell architecture, it...