Workstations & Towers

The NVIDIA DGX Station is the most powerful preconfigured HPC-, AI- and Data Analytics Workstation.

1. Intel Xeon E5-2698 v4, 20 Cores @ 2.2GHz
2. 256GB DDR4-2133 ECC RDIMM
3. Storage:
   • Data: 3x 1,92TB SATA SSD RAID 0
   • OS: 1x 1,92TB SATA SSD
4. 4x watercooled NVIDIA ™ Tesla V100 SXM2 GPUs
5. 2x 10Gbit RJ45 LAN Ports
6. 3x DisplayPort, 2x eSATA, 2x USB 3.1, 4x USB 3.0

Buyers of a DGX station get full access to the NVIDIA GPU Cloud, which provides easy access to a comprehensive catalog of GPU-optimized software. The NVIDIA Cloud features performance-engineered containers with all the top deep learning frameworks such as TensorFlow, PyTorch, MXNet, and more, tuned, tested, certified, and maintained by NVIDIA.
GPU accelerated analytics and interactive visualization solutions provide deeper insights, enable dynamic correlation, and deliver predictive outcomes at superhuman speed, accuracy and scale.
The NVIDIA GPU Cloud also includes third-party managed containers for HPC applications, and NVIDIA containers for HPC visualization.
This product is eligible for a NVIDIA Education rabate. If you are eligible for an education rebate or want to have it checked, please press the blue button.

If you do not belong to a university or similar educational institution, please click on the orange Add button in the left column.

DGX Station Education Inquiry Form

High end deep learning power with up to 4x GPUs and 2 Intel® Xeon® CPUs stays cool and quiet with a complete water-cooling system.

The devCUBE is one of the best deskside solutions for deep learning and we are proud to present its even cooler brother: The devCUBE H₂O – a sysGen Original

• Complete water-cooling System - silent high-end performance
• Ready to Go System - completely configured, incl. all required Software
• NVIDIA DIGITS software providing powerful design, training, and visualization of deep neural networks for image classification

1. Dual Intel Xeon E5-2687W v4 CPUs with up to 3.5 GHz each
2. Highest level of silent computing with a system wide, low maintenance water-cooling system
3. Pre-Installed and Pre-configured software package for deep learning
Pre-installed Ubuntu with Caffe, Torch, Theano, BIDMach, cuDNN and CUDA
Pre-requisite: Before sysGen can install cuDNN , you have to successfully register on the NVIDIA website as a system developer for "Deep Learning" and sign the NVIDIA "CUDA Software Distribution Agreement for Toolkit cuDNN".
4. Up to 512GB ECC DDR4 LR-DIMM / RegDIMM Memory
5. Space for 6x SSDs / HDDs, 1x M.2
6. 2 x Gigabit LAN via Intel® I210-AT

Fields of Application:

sysGen configurable Workstation

Hardware:

1. Supports Intel Xeon W Processors
2. Up to 512GB DDR4 ECC reg/LR RAM
3. 2x 10GbE RJ45
4. Up to 2x NVIDIA™ Quadro RTX 8000 or Quadro RTX 6000
5. Up to 2x M.2 NVME SSDs
6. Up to 4x 2.5" Drive Bays
7. 2x 5.25" Drive Bays for Storage Extensions
8. High-Airflow for cooler GPUs or other PCIe Cards
9. NVLINKX16-2SLOT-PB Quadro RTX SLI NVLink HB included

NVIDIA DS Workstation Software Load:

• NVIDIA® CUDA-X AI™ accelerated data science software, such as RAPIDS™, TensorFlow, PyTorch and Caffe. CUDA-X AI is a collection of libraries that enable modern computing applications to benefit from NVIDIA’s GPU-accelerated computing platform. These data science workstations make it easy for scientists to wrangle, prep, train and deploy models quickly and accurately
• Get started right away without wasting time. We've installed (almost) everything you need
• optional Partner ECO systems of your choice, like OmniSci, BlazingDB, ...

Pricing below is for an unconfigured product

Fields of Application:

sysGen complete workstation, modifications possible

Hardware:

1. Intel Xeon W-2155, 10 Cores @ 3.30GHz
2. 256GB DDR4 ECC reg | Upgradable to 512GB
3. 2x 10GbE RJ45
4. First NVIDIA™ Quadro RTX 6000 included, second GPU card optional
5. 2x Micron 2200 512GB M.2 SSDs | RAID1
6. 4x Micron 5200 Pro 1,92TB SATA SSDs | RAID0
7. Optional Memory Expansion Kit with Memory Drive SSDs
8. High-Airflow for cooler GPUs or other PCIe Cards

NVIDIA DS Workstation Software Load:

• Get started right away without wasting time. We've installed (almost) everything you need
• NVIDIA® CUDA-X AI™ accelerated data science software, such as RAPIDS™, TensorFlow, PyTorch and Caffe. CUDA-X AI is a collection of libraries that enable modern computing applications to benefit from NVIDIA’s GPU-accelerated computing platform. These data science workstations make it easy for scientists to wrangle, prep, train and deploy models quickly and accurately
• optional Partner ECO systems of your choice, like OmniSci, BlazingDB, ...

Fields of Application:

sysGen complete workstation, modifications possible

Hardware:

1. Intel Xeon W-2155, 10 Cores @ 3.30GHz
2. 256GB DDR4 ECC reg | Upgradable to 512GB
3. 2x 10GbE RJ45
4. First NVIDIA™ Quadro RTX 8000 included, second GPU card optional
5. 2x Micron 2200 512GB M.2 SSDs | RAID1
6. 4x Micron 5200 Pro 1,92TB SATA SSDs | RAID0
7. Optional Memory Expansion Kit with Memory Drive SSDs
8. High-Airflow for cooler GPUs or other PCIe Cards

NVIDIA DS Workstation Software Load:

• Get started right away without wasting time. We've installed (almost) everything you need
• NVIDIA® CUDA-X AI™ accelerated data science software, such as RAPIDS™, TensorFlow, PyTorch and Caffe. CUDA-X AI is a collection of libraries that enable modern computing applications to benefit from NVIDIA’s GPU-accelerated computing platform. These data science workstations make it easy for scientists to wrangle, prep, train and deploy models quickly and accurately
• optional Partner ECO systems of your choice, like OmniSci, BlazingDB, ...

Fields of Application:

sysGen configurable Workstation

Hardware:

1. Supports Intel Xeon W Processors
2. Up to 512GB DDR4 ECC reg/LR RAM
3. 2x 10GbE RJ45
4. First NVIDIA™ Quadro RTX 6000 included, second GPU card optional
5. Up to 2x M.2 NVME SSDs
6. Up to 4x 2.5" Drive Bays
7. 2x 5.25" Drive Bays for Storage Extensions
8. High-Airflow for cooler GPUs or other PCIe Cards
9. NVLINKX16-2SLOT-PB Quadro RTX SLI NVLink HB included

NVIDIA DS Workstation Software Load:

• NVIDIA® CUDA-X AI™ accelerated data science software, such as RAPIDS™, TensorFlow, PyTorch and Caffe. CUDA-X AI is a collection of libraries that enable modern computing applications to benefit from NVIDIA’s GPU-accelerated computing platform. These data science workstations make it easy for scientists to wrangle, prep, train and deploy models quickly and accurately
• Get started right away without wasting time. We've installed (almost) everything you need
• optional Partner ECO systems of your choice, like OmniSci, BlazingDB, ...

Fields of Application:

sysGen configurable Workstation

Hardware:

1. Supports Intel Xeon W Processors
2. Up to 512GB DDR4 ECC reg/LR RAM
3. 2x 10GbE RJ45
4. First NVIDIA™ Quadro RTX 8000 included, second GPU card optional
5. Up to 2x M.2 NVME SSDs
6. Up to 4x 2.5" Drive Bays
7. 2x 5.25" Drive Bays for Storage Extensions
8. High-Airflow for cooler GPUs or other PCIe Cards
9. NVLINKX16-2SLOT-PB Quadro RTX SLI NVLink HB included

NVIDIA DS Workstation Software Load:

• NVIDIA® CUDA-X AI™ accelerated data science software, such as RAPIDS™, TensorFlow, PyTorch and Caffe. CUDA-X AI is a collection of libraries that enable modern computing applications to benefit from NVIDIA’s GPU-accelerated computing platform. These data science workstations make it easy for scientists to wrangle, prep, train and deploy models quickly and accurately
• Get started right away without wasting time. We've installed (almost) everything you need
• optional Partner ECO systems of your choice, like OmniSci, BlazingDB, ...

sysGen devCUBE ™ Workstation, consisting of:
Carbide Air 540 Desk-side housing with 1600/1700 Watt 80+ Platinum/Titanium Power Supply and Intel Xeon W compatible Mainboard
Chassis Features:

1. Supports Intel Xeon W CPUs
2. Supports up to 512GB of DDR4 ECC RDIMM/LRDIMM
3. Supports up to 2x Dual-Slot TITAN RTX GPUs
4. 8x SATA3, 2x M.2 and 2x U.2 NVME onboard
5. Up to 4x 2.5" HDDs or SSDs
6. Up to 2x 3.5" HDDs
7. 2x 5.25" Peripheral Drive Bays
8. High-Airflow for cooler GPUs or other PCIe Cards

sysGen devCUBE ™ workstation barebone with Carbide Air 540 Desk-side enclosure, 1600/1700 Watt Titanium Level Power Supply and AMD EPYC compatible Mainboard

• AI, Machine and Deep Learning
• Data Science
• Data Visualization
• High Performance Computing

1. Supports 1x AMD EPYC CPUs
2. Supports up to 1TB of DDR4 ECC RDIMM/LRDIMM in 8 DIMMs
3. Supports up to 4x Dual-Slot GPUs
4. 8x SATA3, 2x M.2 and 2x U.2 NVME onboard
5. Up to 4x 2.5" HDDs or SSDs
6. Up to 2x 3.5" HDDs
7. 2x 5.25" Peripheral Drive Bays
8. High-Airflow for cooler GPUs or other PCIe Cards

For the following GPU cards NVIDIA will grant full access to the NVIDIA NGC cloud software. In additon you have full access to our preinstalled sysGen Learning Image. All software containers are tuned, tested, certified, and maintained for the top frameworks:

• NVIDIA Quadro RTX Series (RTX 4000/5000/6000/8000)
• NVIDIA Quadro GV100
• NVIDIA RTX Titan
• NVIDIA GeForce RTX 2080 Ti

sysGen devCUBE ™ Workstation, consisting of:
Carbide Air 540 Desk-side housing with 1600/1700 Watt 80+ Platinum/Titanium Power Supply and an AMD Threadripper compatible Mainboard

1. Supports AMD Threadripper CPUs
2. Supports up to 128GB of DDR4 ECC UDIMM
3. Supports up to 4x Dual-Slot GPUs
4. 8x SATA3, 3x M.2 and 1x U.2 NVME onboard
5. Up to 4x 2.5" HDDs or SSDs
6. Up to 2x 3.5" HDDs
7. 2x 5.25" Peripheral Drive Bays
8. High-Airflow for cooler GPUs or other PCIe Cards

1. Dual socket P (LGA 3647) supports Intel® Xeon® Scalable Processors, Dual UPI up to 10.4GT/s
2. Up to 2TB ECC 3DS LRDIMM, up to DDR4-2666MHz; 16 DIMM slots
3. 4 PCI-E 3.0 x16, 2 PCI-E 3.0 x8 slots
4. 2x 1GbE LAN ports
5. 7.1 HD Audio
6. 4 Internal fixed 3.5" drive bays, 2 5.25" peripheral drive bays
7. 1200W High-efficiency Power Supply Platinum Level Certified

1. Dual socket P (LGA 3647) supports Intel® Xeon® Scalable Processors, Dual UPI up to 10.4GT/s
2. Up to 2TB ECC 3DS LRDIMM, up to DDR4-2666MHz; 16 DIMM slots
3. 4 PCI-E 3.0 x16, 2 PCI-E 3.0 x8 slots
4. 2x 1GbE LAN ports
5. 7.1 HD Audio
6. 8 Hot-swap 3.5" SAS3/SATA3 drive bays (SATA3 dafault), 1 M.2 slot, 2 NVMe support with opt. cables
7. 1200W High-efficiency Power Supply Platinum Level Certified

• Cost Effective

1. Dual socket P (LGA 3647) supports Intel® Xeon® Scalable Processors, Dual UPI up to 10.4GT/s
2. Up to 2TB ECC 3DS LRDIMM, up to DDR4-2666MHz; 16 DIMM slots
3. 4 PCI-E 3.0 x16, 2 PCI-E 3.0 x8 slots
4. 8 Hot-swap 3.5" SATA3 drive bays; RAID 0, 1, 5, 10
5. Optional DVD-ROM drive, optional support: 2 fixed 2.5" NVMe/SSD/HDD, 1 M.2 support
6. 3 Peripheral 5.25" bays
7. 2x 10GBase-T LAN ports with Intel X722
8. 1280W Redundant Power Supplies Platinum Level (94%)

• Cost Effective

1. Dual socket P (LGA 3647) supports Intel® Xeon® Scalable Processors, Dual UPI up to 10.4GT/s
2. Up to 2TB ECC 3DS LRDIMM, up to DDR4-2666MHz; 16 DIMM slots
3. 4 PCI-E 3.0 x16, 2 PCI-E 3.0 x8 slots
4. 8 Hot-swap 3.5" SATA3 drive bays; RAID 0, 1, 5, 10
5. Optional DVD-ROM drive, optional support: 2 fixed 2.5" NVMe/SSD/HDD, 1 M.2 support
6. M.2 Interface: PCI-E 3.0 x4 M.2 Form Factor: 2260, 2280, 22110 M.2 Key: M-Key
7. 3 Peripheral 5.25" bays
8. 2x 1GbE LAN ports with Intel® X722
9. 1280W Redundant Power Supplies Platinum Level (94%)

The bitCUBE offers as an all-in-one-solution a compact and safe transportation of huge amounts of date (up to 23 TB per bitCUBE) between various locations with up to 4GB per second.

The bitCUBE works with the bitWARE software package - designed by sysGen.

• Up to 23TB portable SSD memory
• Fast transfer via 40Gb/s InfiniBand and up to 4 Gigabyte per second
• Extensive software package with intuitive user interface and management solutions designed by sysGen
• On-site operational via touchscreen

1. Up to 23TB SSD memory secured and accelerated with RAID z2 (ZFS)
2. Small robust aluminum case, portable with handle and touchscreen
3. Transfere rates up to 4 Gigabyte per second
4. Fast Infiniband connection with 40Gb/s
5. Versatile and powerful software package for servers and clients with wizards and intuitive user interface