GPU Servers

Equipped with graphics processors, these servers are configured for intensive use. Thanks to their computing power, GPU servers are designed to speed up parallel task processing.

Product Recommendation

You will own managed dedicated servers hosted in VPB data center
and 24/7/365 fully online tech support by VPB's engineers.

NVIDIA GeForce GTX 1070 & GTX 1080

These two latest-generation Nvidia graphics cards are based on “Pascal” architecture. They can be used for 3D graphics acceleration or as a co-processor to perform calculations with simple precision, thanks to their CUDA cores. The 4 GPU configurations are specifically designed for use in "Cloud gaming" by hosting virtual machines linked to a dedicated "passthrough" graphics card .
Geforce GTX 1070:


1920 CUDA cores

Max bandwidth of 256 GB/s

Nvidia GPU Boost 3.0 Technology

Geforce GTX 1070:


1920 CUDA cores

Max bandwidth of 256 GB/s

Nvidia GPU Boost 3.0 Technology

Compatible with: Linux, CUDA/OpenCL, KVM.


The card’s 1664 CUDA cores process parallel workloads for accelerated video encoding.

3D rendering

Harness the GPU’s computing power to generate your animations/images.


Leverage the computing power to develop and test your CUDA/OpenCL applications.

NVIDIA Tesla M60

The M60 is part of the NVIDIA server range for professionals. It was specifically designed for virtualization and uses NVIDIA GRID technology to allow up to 32 concurrent users to share the graphics card resources!The Nvidia M60 card enables the deployment of virtualized infrastructures, boasting graphics acceleration to meet the needs of advanced users (graphic designers/engineers). It provides the flexibility of virtualized desktops (VDI), while still offering the graphics power required to run 3D applications (DirectX/OpenGL).

Dual GPU design (Two Maxwell GPUs)

4096 CUDA cores

DDR5 16 GB

320 Gbps max bandwidth

Compatible: VMWare ESXi, Citrix Xenserver, KVM.


Combine Nvidia technology with market leading hypervisors to build high-performance VDI infrastructures.

Cloud 3D

Provide your users (Architects, Designers) with remote workstations for their 3D applications.

Cloud Gaming

Outsource GPU to the Cloud in order to host demanding applications such as online games.

NVIDIA Tesla K80

One of the fastest GPU accelerators in the world: optimized for high-performance computing and machine learning. It is between 5 and 10 times faster than classic CPU configurations.

Dual GPU design (Two Kepler GK210 GPUs per card)

4992 CUDA cores

DDR5 24 GB

480 Gbps bandwidth

Linux, Windows Server, CUDA/OpenCL.

High-performance computing

Unleash the card’s CUDA/OpenCL capabilities to accelerate processing of your HPC applications.

Machine learning

Take advantage of the computing power of the GPU to optimize machine learning techniques.


Use the card’s 4992 GPU cores for the parallel processing of your bioinformatics data.

Why GPU?

A GPU (Graphical Process Unit), has a massively parallel architecture compared to a conventional CPU. This design originally intended to handle computation only for computer graphics (OpenGL/Direct3D), was adapted with programming languages such as CUDA or OpenCL, to perform computation in applications traditionally handled by CPU.

Due to its ability to speed up processing, GPU architecture is particularly suited to resource-intensive applications which require a large number of parallel tasks (image processing, bioinformatics, big data ... ).

Custom Servers Yourself

VPB.COM custom servers solutions offers the highest value and maximum flexibility configure to meet your budget and performance requirements.

Custom Servers Quote Request