# Nvidia H100b200 Nvl72 Cluster

> Publicly sourced profile assembled by Optimly, in the Optimly AI Brand Index. Last refreshed 2026-10-04.

- **Business Profile:** https://optimly.ai/brand/nvidia-h100b200-nvl72-cluster
- **Dataset:** https://optimly.ai/brand/nvidia-h100b200-nvl72-cluster.json
- **Markdown:** https://optimly.ai/brand/nvidia-h100b200-nvl72-cluster/llms.txt
- **Official website:** https://nvidia.com
- **Slug:** nvidia-h100b200-nvl72-cluster
- **Categories:** cloud-infrastructure, data-centers, enterprise-servers-storage, semiconductors

## Overview

- **Tagline:** The NVL72 rack acts as a single massive GPU with 72 chips interconnected via a 130TB/s liquid-cooled backplane.
Source: Brand's website (https://nvidia.com) · 2026-10-04

- **Description:** A technical configuration string representing a high-performance computing (HPC) environment utilizing Nvidia's H100 (Hopper) and B200 (Blackwell) GPUs within an NVL72 rack architecture. It refers to a liquid-cooled, high-density AI data center solution designed for training trillion-parameter large language models.
Source: Brand's website (https://nvidia.com) · 2026-10-04

## Offerings

- **Core capabilities:**
  - Nvidia H100 GPUs
  - Nvidia B200 Blackwell GPUs
  - GB200 NVL72 Rack Architecture
  - NVLink Interconnects
Source: Brand's website (https://nvidia.com) · 2026-10-04

- **Pricing:** Enterprise/Custom (multi-million dollar deployments)
Source: Brand's website (https://nvidia.com) · 2026-10-04

## Audience

- **Target industry:** Hyperscale Cloud Providers, Sovereign AI Initiatives, Elite Research Labs, Tier-1 Enterprises (Tesla, Meta, etc.)
Source: Brand's website (https://nvidia.com) · 2026-10-04

## Landscape

- **Competitors:**
  - AMD Instinct MI300X/MI325X Clusters
  - Google TPU v5p Clusters (Cloud TPU)
  - Intel Gaudi 3 AI Accelerators
Source: Brand's website (https://nvidia.com) · 2026-10-04

Page last updated 2026-10-17.