NVIDIA DGX™ B200

The foundation for your AI center of excellence.

NVIDIA DGX™ B200 delivers a unified platform for training, fine-tuning and inference in a single solution optimized for enterprise and powered by NVIDIA Blackwell.

Access the Technical Sheet Connect with Our Team

PUSHING THE BOUNDARIES OF AI Revolutionary Performance Backed by Evolutionary Innovation

NVIDIA DGX™ B200 is an unified AI platform for develop-to-deploy pipelines for businesses of any size at any stage in their AI journey. Equipped with eight NVIDIA Blackwell GPUs interconnected with fifth-generation NVIDIA® NVLink®, NVIDIA DGX™ B200 delivers leading-edge performance, offering 3X the training performance and 15X the inference performance of previous generations.

Leveraging the NVIDIA Blackwell GPU architecture, NVIDIA DGX™ B200 can handle diverse workloads—including large language models, recommender systems, and chatbots—making it ideal for businesses looking to accelerate their AI transformation.

Download the Ebook

PNY ADDED VALUE SERVICES

Presales Support

Our team of experts collaborates with clients to understand their unique needs, guiding them toward the optimal solutions for their specific challenges.

Proof Of Concept Support

We also provide POC Support, ensuring our clients can try before they buy with testing, benchmarks and evaluation.

Logistics & Operations

To drive you "To Success", we provide Strong Logistic and Operation Abilities, guaranteeing seamless deployment.

Installation Service Support

To keep it all running smoothly, we provide Installation Services Support, ensuring that our solutions are properly installed and configured for optimal performance.

PERFORMANCE Next-Generation Performance
Powered by NVIDIA DGX B200

Real Time Large Language Model Inference

Projected performance subject to change. Token-to-token latency (TTL) = 50ms real time, first token latency (FTL) = 5s, input sequence length = 32,768, output sequence length = 1,028, 8x eight-way NVIDIA DGX™ H100 GPUs air-cooled vs. 1x eight-way NVIDIA DGX™ B200 air-cooled, per GPU performance comparison.

Supercharged AI Training Performance

Projected performance subject to change. 32,768 GPU scale, 4,096x eight-way NVIDIA DGX™ H100 air-cooled cluster: 400G IB network, 4,096x 8-way NVIDIA DGX™ B200 air-cooled cluster: 400G IB network.

BENEFITS A UNIFIED AI FACTORY

One Platform for Develop-to-Deploy Pipelines

Enterprises require massive amounts of compute power to handle complex AI datasets at every stage of the AI pipeline, from training to fine-tuning to inference. With NVIDIA DGX™ B200, enterprises can arm their developers with a single platform built to accelerate their workflows.

Powerhouse of AI Performance

Powered by the NVIDIA Blackwell architecture’s advancements in computing, NVIDIA DGX™ B200 delivers 3X the training performance and 15X the inference performance of NVIDIA DGX™ H100. As the foundation of NVIDIA DGX BasePOD™ and NVIDIA DGX SuperPOD™, NVIDIA DGX™ B200 delivers leading-edge performance for any workload.

Proven Infrastructure Standard

NVIDIA DGX™ B200 is a fully optimized hardware and software platform that includes the complete NVIDIA AI software stack, including NVIDIA Base Command and NVIDIA AI Enterprise software, a rich ecosystem of third-party support, and access to expert advice from NVIDIA professional services.

GET IN TOUCH

Follow PNY Pro

Sign Up Now

Transform your data center operations! Join our newsletter to receive exclusive podcasts, virtual events, and expert information on data center and networking innovations.