NVIDIA DGX solutions - sysGen GmbH

The future of AI computing
NVIDIA DGX systems
- View DGX products

Organisations that deploy next-generation AI are 2.6 times more likely to increase revenue by at least 10%. The NVIDIA DGX™ platform is the proven standard for enterprise AI, helping organisations benefit from advanced language models and generative AI to drive innovation and secure competitive advantage.

Complete AI solutionNVIDIA DGX™ software stack

Complete AI solution

NVIDIA DGX™ software stack

The DGX platform integrates NVIDIA Base Command™ and NVIDIA AI Enterprise - a comprehensive software suite for optimising AI development.

Features of the software:

Cluster Management: Facilitates provisioning, monitoring and management.
MLOps & Workflow Optimisation: Supports Kubernetes and SLURM for seamless orchestration.
Accelerated Infrastructure: Optimised libraries for network, storage and data operations.

These features enable organisations to scale smoothly and accelerate time to market for AI applications.

NVIDIA DGX systemsThe basis for innovation

NVIDIA DGX systems

The basis for innovation

DGX B200: A unified platform for training, fine-tuning and inference. The NVIDIA Blackwell architecture offers 3x more AI training and 15x more inference performance than its predecessors.
DGX H200: Leads organisations to new dimensions of innovation with Tensor Core GPU technology.
DGX BasePOD™: Scalable solution for industry-specific use cases, from healthcare to finance to manufacturing
DGX SuperPOD™: Industry-leading AI infrastructure for maximum performance and scalability.

Products

DGX stands for a future in which AI boundaries are redefined

NVIDIA DGX H200 1128GB The Universal System for AI Infrastructure

CPU

2x Intel Xeon Platinum 8480C (56 Cores, 2.0GHz)

RAM

2TB

SSD

2x 1.9TB NVMe M.2
8x 3.84TB NVMe U.2

GPU

8x NVIDIA H200 141GB

Network

4x OSFP (8x single-port 400Gb/s InfiniBand/Ethernet)
2x dual-port NVIDIA ConnectX-7 VPI
1x 400Gb/s InfiniBand/Ethernet
1x 200Gb/s InifniBand/Ethernet

Warranty

includes 3 years NVIDIA Business-Standard Support

EDU

NVIDIA bietet einen EDU-Rabatt für Forschung und Lehre für dieses Produkt an, fragen Sie diesen bitte mit an.

On Request

Request Now

NVIDIA DGX B200-180GB The Universal System for AI Infrastructure

CPU

2x Intel Xeon Platinum 8570 (56 Cores, 2.1GHz)

RAM

2TB (Optional: up to 4TB)

SSD

2x 1.9TB NVMe M.2
8x 3.84TB NVMe U.2

GPU

8x NVIDIA B200 180GB

Network

4x OSFP (8x single-port 400Gb/s InfiniBand/Ethernet)
2x dual-port QSFP112 NVIDIA BlueField-3 DPU
Up to 400Gb/s InfiniBand/Ethernet
10Gb/s onboard NIC with RJ45
100Gb/s dual-port ethernet NIC
Host baseboard management controller (BMC) with RJ45

Support

Includes 3 years NVIDIA Business Standard Support

EDU

NVIDIA bietet einen EDU-Rabatt für Forschung und Lehre für dieses Produkt an, fragen Sie diesen bitte mit an.

On Request

Request Now

NVIDIA DGX B300 2.3 TB The AI factory foundation for AI reasoning

CPU

2x Intel Xeon 6776P

SSD

2 x 1,9 TB NVMe M.2
8 x 3,84 TB NVMe E1. S

GPU

NVIDIA Blackwell Ultra-GPUs

Network

8x OSFP-Ports für 8 x NVIDIA ConnectX-8 VPI (bis zu 800 Gbit/s)
2x Dual-Port QSFP112 NVIDIA BlueField-3 DPU (bis zu 400 Gbit/s)
1-GbE Onboard-NIC mit RJ45
1-GbE RJ45 Host-Baseboard Management Controller (BMC)

Support

Includes 3 years NVIDIA Business Standard Support

EDU

NVIDIA bietet einen EDU-Rabatt für Forschung und Lehre für dieses Produkt an, fragen Sie diesen bitte mit an.

On Request

Request Now

NVIDIA DGX Spark A Grace Blackwell AI supercomputer on your desk

GPU

NVIDIA Blackwell Architecture

CPU

20 core Arm, 10 Cortex-X925 + 10 Cortex-A725 Arm

RAM

128 GB LPDDR5x, unified system memory

SSD

1 or 4 TB NVME.M2 with self-encryption

Network

1x RJ-45 connector 10 GbE

Warranty

includes 3 years NVIDIA Business-Standard Support

On Request

Request Now

Why NVIDIA DGX?

NVIDIA DGX™ systems are specifically designed to meet the demands of artificial intelligence. They set the standard for organisations that want to use AI-powered insights to achieve their business goals. Whether it's customer experience, patient outcomes or process optimisation, DGX systems deliver the performance and scalability you need.

NVIDIA DGX in use

From accelerating machine learning training and advanced data analytics to enabling new research breakthroughs in science, NVIDIA DGX systems are the foundation for innovative AI projects worldwide.

NVIDIA DGX platformThe proven solution for companies

NVIDIA DGX platform

The proven solution for companies

The NVIDIA DGX platform combines the best of NVIDIA's technologies, software and infrastructure into a modern, unified AI solution. It is specifically designed to enable organisations to deliver high-performance AI development and training. From hardware to software, every element of the DGX platform is characterised by NVIDIA expertise, enabling companies to benefit faster from their AI investments.

Highlights of the NVIDIA DGX platform:

High performance: leading AI systems optimised for the toughest challenges.
Scalability: Flexible deployment from on-premises to cloud.
Support: Direct access to NVIDIA DGXperts for strategic advice.
Energy efficiency: Maximum performance with minimum energy consumption.

NVIDIA DGX systems in comparison

	NVIDIA DGX B300 Blackwell Ultra architecture	NVIDIA DGX B200 Blackwell architecture	NVIDIA DGX H200 Hopper architecture	NVIDIA DGX H100 Hopper architecture (EOL)
GPU	8x NVIDIA Blackwell Ultra Tensor Core GPUs	8x NVIDIA Blackwell Tensor Core GPUs	8x NVIDIA Hopper Tensor Core GPUs	8x NVIDIA Hopper Tensor Core GPUs
GPU Memory	2,300GB total (8x 288GB) HBM3e	1,440GB total (8x 180GB) HBM3e	1,128GB total (8x 141GB) HBM3e	640GB total (8x 80GB) HBM3
Performance	72 petaFLOPS training and 144 petaFLOPS inference	72 petaFLOPS training and 144 petaFLOPS inference	32 petaFLOPS FP8	32 petaFLOPS FP8
NVIDIA® NVSwitch™	2x	2x	4x	4x
System Power Usage	~14.3kW max	~14.3kW max	~10.2kW max	~10.2kW max
CPU	2 Intel® Xeon® Platinum 6776P Processors	2 Intel® Xeon® Platinum 8570 Processors Processors 112 cores total, 2.10 GHz (Base), 4.00 GHz (Max Boost)	2 Intel® Xeon® Platinum 8480C Processors Processors 112 Cores total, 2.00 GHz (Base), 3.80 GHz (Max Boost)	2 Intel® Xeon® Platinum 8480C Processors Processors 112 cores total, 2.00 GHz (Base), 3.80 GHz (Max Boost)
System Memory	-	Up to 4TB	Up to 2TB	Up to 2TB
Networking	8x OSFP ports serving 8x single-port NVIDIA ConnectX-8 VPI 2x dual-port QSFP112 NVIDIA BlueField-3 DPU	4x OSFP ports serving 8x single-port NVIDIA ConnectX-7 VPI 2x dual-port QSFP112 NVIDIA BlueField-3 DPU	4x OSFP ports serving 8x single-port NVIDIA ConnectX-7 VPI 2x dual-port QSFP112 NVIDIA ConnectX-7 VPI	4x OSFP ports serving 8x single-port NVIDIA ConnectX-7 VPI 2x dual-port QSFP112 NVIDIA ConnectX-7 VPI
Management Network	1Gb/s onboard NIC with RJ45 1Gb/s dual-port ethernet NIC Host baseboard management controller (BMC) with RJ45	10Gb/s onboard NIC with RJ45 100Gb/s dual-port ethernet NIC Host baseboard management controller (BMC) with RJ45	10Gb/s onboard NIC with RJ45 100Gb/s dual-port ethernet NIC Host baseboard management controller (BMC) with RJ45	10Gb/s onboard NIC with RJ45 100Gb/s dual-port ethernet NIC Host baseboard management controller (BMC) with RJ45
Storage	OS:2x 1.9TB NVMe M.2 Internal storage: 8x 3.84TB NVMe U.2	OS:2x 1.9TB NVMe M.2 Internal storage: 8x 3.84TB NVMe U.2	OS:2x 1.9TB NVMe M.2 Internal storage: 8x 3.84TB NVMe U.2	OS:2x 1.9TB NVMe M.2 Internal storage: 8x 3.84TB NVMe U.2
Software	NVIDIA AI Enterprise - Optimised AI Software NVIDIA Base Command - Orchestration, Scheduling, and Cluster Management DGX OS / Ubuntu - Operating System	NVIDIA AI Enterprise - Optimised AI Software NVIDIA Base Command - Orchestration, Scheduling, and Cluster Management DGX OS / Ubuntu - Operating System	NVIDIA AI Enterprise - Optimised AI Software NVIDIA Base Command - Orchestration, Scheduling, and Cluster Management DGX OS / Ubuntu - Operating System	NVIDIA AI Enterprise - Optimised AI Software NVIDIA Base Command - Orchestration, Scheduling, and Cluster Management DGX OS / Ubuntu - Operating System
Height units	10U	10U	8U	8U
System dimensions		HxWxL (444mm x 482mm x 897mm)	HxWxL (356mm x 482mm x 897mm)	HxWxL (356mm x 482mm x 897mm)
Support	Includes 3 years NVIDIA Business Standard Support	Includes 3 years NVIDIA Business Standard Support	Includes 3 years NVIDIA Business Standard Support	Includes 3 years NVIDIA Business Standard Support

Suitable AI systems

NVIDIA DGX SuperPOD

Industry-leading full-cycle infrastructure - the fastest path to AI innovation at scale.

Learn more

HGX AI supercomputer

Massive data sets, huge deep learning models and complex simulations require multiple graphics processors with extremely fast connections and a fully accelerated software stack.

Learn more

Questions about NVIDIA DGX?

Allgemeine Daten

Firma / Organisation

Anrede

Vorname

Nachname

PLZ

Straße Nr.

Ort

Land

E-Mail

Telefon

Fax

Industrie / Branche

Abteilung / Fachbereich

Referenz Seite

Weitere Informationen

Fragen oder Informationen?

Datenschutzerklärung

Ja, ich habe die Datenschutzerklärung zur Kenntnis genommen und bin damit einverstanden, dass die von mir angegebenen Daten elektronisch erhoben und gespeichert werden. Meine Daten werden dabei nur streng zweckgebunden zur Bearbeitung und Beantwortung meiner Anfrage benutzt. Mit dem Absenden des Kontaktformulars erkläre ich mich mit der Verarbeitung einverstanden.

Relevant solution on the topic of AIEngineering Simulation, Scientific Research, Genomic Sequencing, Drug Discovery

Relevant solution on the topic of AI

Engineering Simulation, Scientific Research, Genomic Sequencing, Drug Discovery

To shorten the time to discovery for scientists, researchers and engineers, more and more HPC workloads are being augmented with machine learning algorithms and GPU-accelerated parallel computing. Many of the world's fastest supercomputing clusters now utilise GPUs and the power of AI.

HPC workloads typically require data-intensive simulations and analyses with massive data sets and precision requirements. GPUs like NVIDIA's H100/H200 offer unprecedented performance with double the precision, delivering 60 teraflops per GPU.

Our Supermicro's highly flexible HPC platforms enable high GPU and CPU counts in various dense form factors with rack-scale integration and liquid cooling.