Altair provides NVIDIA-powered GPU solutions for small to large computing requirements in different application frameworks, utilizing the full range of NVIDIA core technologies. Selection of the most appropriate GPU solution in a user’s context is a key requirement for business success.

GPUs

GPUs

GPUs offer the compute power of up to 100 CPUs in a single GPU, enabling scientists to solve problems that were once thought impossible.

Learn More

19

19" Rackmount Server

Inspired by the demands of deep learning and analytics, NVIDIA rackmount systems are essential instruments for AI research, hosted in a data centre to serve teams of researchers.

Learn More

Workstations

Workstations

NVIDIA-powered data science workstations give data scientists everything they need to tackle complex workflows in any location and without requiring data centre installations.

Learn More

GPU Model Information

NVIDIA QUADRO GV100

Peak double precision
Up to 7.4 TeraFLOPS
Peak single precision
Up to 14.8 TeraFLOPS
Deep Learning
Up to 118.5 TeraFLOPS
Number of GPUs
1x VP100
Number of CUDA cores
5120
Number of Tensor cores
640
Memory size per board (HBM2)
32GB at 870 GB/s
Max Power
250W
Features
Volta Architecture pairing NVIDIA® CUDA® and Tensor Cores, Second-Generation NVIDIA® NVLink
System
Workstation
Cooling
Active

NVIDIA TESLA® V100

Peak double precision
up to 7.8 TeraFLOPS
Peak single precision
up to 15.7 TeraFLOPS
Deep Learning
up to 125 TeraFLOPS
Number of GPUs
1x VP100
Number of CUDA cores
5120
Number of Tensor cores
640
Memory size per board (HBM2)
16GB/32GB at 900 GB/s
Max Power
250W (PCIe)/300W (SXM-2)
Features
Volta Architecture pairing NVIDIA® CUDA® and Tensor Cores to deliver the performance of an AI supercomputer in a single GPU
System
Servers NVLINK / PCIe Gen3 / SXM-2
Cooling
Passive

NVIDIA QUADRO RTX 8000

Peak single precision
Up to 16.3 TeraFLOPS
Deep Learning
Up to 130.5 TeraFLOPS
Number of GPUs
1x TU102
Number of CUDA cores
4608
Number of Tensor cores
576
Number of RT cores
72
Memory size per board (GDDR6)
16GB/32GB at 900 GB/s
Max Power
295W
Features
Turing Architecture, NVLink capable, 100GB/s NVLink Bandwith (bidirectional)
System
Workstation, Server
Cooling
Active

NVIDIA QUADRO RTX 6000

Peak single precision
Up to 16.3 TeraFLOPS
Deep Learning
Up to 130.5 TeraFLOPS
Number of GPUs
1x TU102
Number of CUDA cores
4608
Number of Tensor cores
576
Number of RT cores
72
Memory size per board (GDDR6)
24GB at 672 GB/s
Max Power
295W
Features
Turing Architecture, NVLink capable, 100GB/s NVLink Bandwith (bidirectional)
System
Workstation, Server
Cooling
Active

NVIDIA QUADRO RTX 5000

Peak single precision
Up to 11.2 TeraFLOPS
Deep Learning
Up to 89.2 TeraFLOPS
Number of GPUs
1x TU104
Number of CUDA cores
3072
Number of Tensor cores
384
Number of RT cores
48
Memory size per board (GDDR6)
16GB at 448 GB/s
Max Power
265W
Features
Turing Architecture, NVLink capable, 50GB/s NVLink Bandwith (bidirectional)
System
Workstation, Server
Cooling
Active

NVIDIA TESLA® P40 (Inferencing Accelerator)

Peak single precision
12 TeraFLOPS
Integer Operations (INT8)
47 TOPS* (Tera-Operations per Second)
Number of GPUs
1x GP102
Number of CUDA cores
3840
Memory size per board (GDDR5)
24GB at 346GB/s
Max Power
250W
Features
Enhanced Programmability with Page Migration Engine, ECC Protection, Server-Optimized for Data Center Deployment, Hardware-Accelerated Video Engine 1x Decode Engine, 2x Encode Engine
System Interface
PCI Express 3.0 x16
Cooling
Passive

NVIDIA TESLA® P4 (Inferencing Accelerator)

Peak single precision
5.5 TeraFLOPS
Integer Operations (INT8)
22 TOPS* (Tera-Operations per Second)
Number of GPUs
1x GP104
Number of CUDA cores
2560
Memory size per board (GDDR5)
8GB at 192GB/s
Max Power
50W/75W
Features
Enhanced Programmability with Page Migration Engine, ECC Protection, Server-Optimized for Data Center Deployment, Hardware-Accelerated Video Engine 1x Decode Engine, 2x Encode Engine
System Interface
Low-Profile PCI Express Form Factor
Cooling
Passive

NVIDIA TESLA® M60

Peak double precision
0.3 TeraFLOPS
Peak single precision
9.7 TeraFLOPS
Number of GPUs
2 x GM205
Number of CUDA cores
4096 (2x 2048)
Memory size per board (GDDR5)
16 GB (8 GB per GPU)
Memory bandwidth for board (ECC off)
320 GBytes/sec (2x 160 Gb/s)
Max Power
300W (Passive)/240W (Active)
Architecture Features
SMX, Dynamic Parallelism, Hyper-Q
System
Server PCIe
Cooling
Passive/Active

19" Rackmount Server Model Information

NVIDIA® DGX-2H™

GPU
16x Volta GV100 32GB (Total 512GB, 81920 NVIDIA CUDA® Cores, 10240 NVIDIA Tensor Cores, 2 petaFLOPS GPU FP16)
CPU
2x Intel 24-core Xeon® Platinum 8174 3.10GHz
RAM
1.5TB
Storage
OS: 2x 960GB NVME SSDs; DATA: 30TB (8x 3.84TB) NVME SSDs
Network
Dual 10/25/40/50/100 GbE, 8x IB EDR/100GbE
Operating System
Ubuntu Linux Host OS - See Datasheet for Details

NVIDIA® DGX-2™

GPU
16x Volta GV100 32GB (Total 512GB, 81920 NVIDIA CUDA® Cores, 10240 NVIDIA Tensor Cores, 2 petaFLOPS GPU FP16)
CPU
2x Intel 24-core Xeon Platinum 8168 2.7 GHz
RAM
1.5TB
Storage
OS: 2x 960GB NVME SSDs; DATA: 30TB (8x 3.84TB) NVME SSDs
Network
Dual 10/25 GbE, 8x IB EDR/100GbE
Operating System
Ubuntu Linux Host OS - See Datasheet for Details

NVIDIA® DGX-1™ V100 - 32GB

GPU
8x Volta GV100 32GB (Total 256GB, 40960 NVIDIA CUDA® Cores, 5120 NVIDIA Tensor Cores, 960 TFLOPS GPU FP16)
CPU
2x Intel 20-core Xeon E-2698v4 2.20 GHz
RAM
512GB 2133 MHz DDR4 LRDIMM
Storage
4x 1.92 TB SSD RAID 0
Network
Dual 10 GbE, up to 4 IB EDR
Software
Ubuntu Linux Host OS - See Datasheet for Details

NVIDIA QUADRO RTX Server

The NVIDIA QUADRO RTX Server is a highly configurable server reference design that provides the power you need to boost rendering performance on desktop, accelerate offline rendering and provision high-performance virtual workstations, all in a single, flexible solution.

The following is an example configuration:

GPU
4x NVIDIA QUADRO RTX 6000/8000
CPU
2x Intel Xeon Gold 6126 processor
RAM
256GB DDR4
Storage
4x 1.92 TB SSD RAID 0
Networking
Dual 10 GbE

Altair TYPHOON V100

GPU
8x NVIDIA® Tesla™ V100 (16GB/32GB HBM2, 5120 CUDA cores, 640 Tensor cores)
CPU
2x Intel Xeon Skylake-SP GOLD 5118 (12x 2.30Ghz), 16,5MB Cache, DDR4-2400
RAM
256GB GDDR4 PC2400 ECC
Graphics
VGA on board
IPMI
Dual 10 GbE
Storage
2x 1TB Enterprise SSD
Powersupply
3,200Watts (2+1 Redundancy) Efficiency 80 plus Platinum
Chassis
4U Server 19” Rackmountable with high efficiency cooling
Operating System
Windows, Linux

Altair TYPHOON P100 (Compute Server)

GPU
8x NVIDIA® Tesla™ P100 (16GB HBM2, 3584 Cuda Cores)
CPU
2x Intel Xeon Haswell E5-2650v4 (12x 2.20Ghz), 30MB Cache, 9.6GT/s, DDR4-2400
RAM
256GB GDDR4 PC2400 ECC
Graphics
VGA on board
IPMI
IPMI v2.0 compliant
Storage
4x 1TB Enterprise SSD
Powersupply
3,200Watts (2+1 Redundancy) Efficiency 80 plus Platinum
Chassis
4U Server 19” Rackmountable with high efficiency cooling
Operating System
Windows, Linux

Altair TYPHOON P40 (Deep Learning Server)

GPU
8x NVIDIA® Tesla™ P40 (24GB GDDR5, 3840 Cuda Cores)
CPU
2x Intel Xeon Haswell E5-2650v4 (12x 2.20Ghz), 30MB Cache, 9.6GT/s, DDR4-2400
RAM
256GB GDDR4 PC2400 ECC
Graphics
VGA on board
IPMI
IPMI v2.0 compliant
Storage
4x 1TB Enterprise SSD
Powersupply
3,200Watts (2+1 Redundancy) Efficiency 80 plus Platinum
Chassis
4U Server 19” Rackmountable with high efficiency cooling
Operating System
Windows, Linux

Altair 2U TS 4xGPU-2xI8-64

GPU
4x NVIDIA® Tesla™ V100, P100, P40 oder M60
CPU
2x Intel Xeon Haswell E5-2609 v4 (8x 1.70GHz), 20MB Cache, 6.4GT/s, DDR4-1866
RAM
64GB GDDR4 PC1866 ECC expandable
Graphics
VGA on board
IPMI
IPMI v2.0 compliant
Storage
1x 1.0TB S-ATA300, 3x HotSwap SAS/SATA
Powersupply
2000W redundant Gold Level
Chassis
2U 19” Rackmount Chassis with high efficiency cooling
Operating System
Windows, Linux

Altair 1U TS 2xGPU-1xI8-32

GPU
2x NVIDIA® Tesla™ V100, P100, P40 oder M60
CPU
1x Intel Xeon Haswell E5-2609 v4 (8x 1.70GHz), 20MB Cache, 6.4GT/s, DDR4-1866
RAM
32GB GDDR4 PC1866 ECC expendable
Graphics
VGA on board
IPMI
IPMI v2.0 compliant
Storage
1x 1.0TB S-ATA300, 3x HotSwap SAS/SATA
Powersupply
1600W redundant Gold Level
Chassis
1U 19” Rackmount Chassis with high efficiency cooling
Operating System
Windows, Linux

Altair 1U TS V100-SXM-2xI12-128

GPU
4x NVIDIA® Tesla™ V100-SXM2
CPU
2x Intel Xeon Haswell E5-2650v4 (12x 2.20Ghz), 30MB Cache, 9.6GT/s, DDR4-2400
RAM
128GB GDDR4 PC2400 ECC
Graphics
VGA on board
IPMI
IPMI v2.0 compliant
Storage
2x 1.0TB Enterprise SSD
Powersupply
2000W Redundant Titanium Level Power Supplies
Chassis
1U 19” Rackmount Chassis with high efficiency cooling
Operating System
Windows, Linux

Workstation Model Information

Single Socket Workstations

NVIDIA® DGX Station™

GPU
4x Volta GV100 32GB (Total 128GB, 20480 NVIDIA CUDA® Cores, 2560 NVIDIA Tensor Cores,480 TFLOPS GPU FP16)
CPU
Intel 20-core Xeon E-2698v4 2.20 GHz
RAM
256GB 2133 MHz DDR4 LRDIMM
Storage
OS: 1x 1.92 TB SSD; DATA: 3x 1.92 TB SSD RAID 0
Network
Dual 10 Gb LAN
Graphics
3x DisplayPort, 4K resolution
Acoustics
< 35 dB (Water-Cooling)
Powersupply
1,500 W
Software
Ubuntu Desktop Linux OS, DGX Recommended GPU Driver, CUDA Toolkit

Dual Socket Workstations

Altair TWS 4xV100-16GB-2xI12-256

GPU
4x NVIDIA® Tesla™ V100 (16GB HBM2, 5120 CUDA cores, 640 Tensor cores)
CPU
2x Intel Xeon Skylake-SP GOLD 5118 (12x 2.30Ghz), 16,5MB Cache, DDR4-2400
RAM
256GB GDDR4 PC2400 ECC
Graphics
VGA on board
IPMI
IPMI v2.0 compliant
Storage
2x 1TB Enterprise SSD
Powersupply
2000W redundant Gold Level
Chassis
4U Tower Rackmountable with high efficiency cooling
Chassis
Windows, Linux

Altair TWS 4xP100-16GB-2xI12-256 (Compute WS)

GPU
4x NVIDIA® Tesla™ P100 (16GB HBM2, 3584 Cuda Cores)
CPU
2x Intel Xeon Haswell E5-2650v4 (12x 2.20Ghz), 30MB Cache, 9.6GT/s, DDR4-2400
RAM
256GB GDDR4 PC2400 ECC
Graphics
VGA on board
IPMI
IPMI v2.0 compliant
Storage
2x 1TB Enterprise SSD
Powersupply
2000W redundant Gold Level
Chassis
4U Tower Rackmountable with high efficiency cooling
Chassis
Windows, Linux

Altair TWS 4xP40-2xI12-256 (Deep Learning WS)

GPU
4x NVIDIA® Tesla™ P40 (24GB GDDR5, 3840 Cuda Cores)
CPU
2x Intel Xeon Haswell E5-2650v4 (12x 2.20Ghz), 30MB Cache, 9.6GT/s, DDR4-2400
RAM
256GB GDDR4 PC2400 ECC
Graphics
VGA on board
IPMI
IPMI v2.0 compliant
Storage
4x 1TB Enterprise SSD
Powersupply
2000W redundant Gold Level
Chassis
4U Tower Rackmountable with high efficiency cooling
Chassis
Windows, Linux

Latest News

Rendering

Rendering

Accelerate your Rendering with the new Quadro RTX Server

Read More

GPU Performance

GPU Performance

Boosting your GPU Performance in a Highly Complex HPC Environment

Read More

AI

AI

Take your AI Research to New Heights

Read More

Be the first to know

Subscribe to our newsletter to learn about product training, news, events, and more!