GPU cloud servers

immers.cloud platform

All of GPU servers are based on Intel® Xeon® Scalable (Cascade Lake) second generation central processors and contain up to 96 virtual processors and up to 512 GB of DDR4 ECC Reg 2400—2933 MHz RAM.

Each processor contains two Intel® AVX-512 units and supports Intel® AVX-512 Deep Learning Boost functions. This set of instructions speeds up multiplication and addition operations with reduced accuracy, which are used in many internal cycles of the deep learning algorithm.

Local storage is organized on Intel® solid-state drives that are designed specifically for data centers and have a capacity of up to 1.92 TB.

GPU RTX^™ 3090

RTX 3090 graphics cards are based on the powerful Ampere architecture and a improved RTX hardware ray tracing platform. Each accelerator has 328 tensor cores, 10496 CUDA cores, and 24 GB of memory.

GPU RTX^® A5000

The RTX A5000 graphics accelerator has the perfect balance of power, performance and reliability to solve complex tasks. This GPU is built on the basis of the latest Ampere architecture and has 24 GB of video memory — everything so that designers, engineers and artists can implement the projects they dreamed of today.

GPU RTX^™ 3080

RTX 3080 graphics cards are based on the powerful Ampere architecture and a improved RTX hardware ray tracing platform. Each accelerator has 272 tensor cores, 8704 CUDA cores, and 10 GB of memory.

GPU Tesla^® A100 80 GB

Tesla A100 GPU provides unsurpassed acceleration for AI tasks, data analysis and for solving the most complex computing tasks. The A100 is the most productive integrated platform for AI and HPC, allowing you to get real-time results and deploy scalable solutions.

GPU Tesla^® A10

Tesla A10 graphics accelerators with tensor cores are built on the Ampere architecture.

Support for Tensor Float 32 (TF32) operations allows you to speed up the training of models for artificial intelligence (AI) and data processing by 5 times compared to the previous generation without changes in the code. Tensor cores also provide AI-based technologies such as DLSS, noise reduction, and photo and video editing functions in some applications.

PCI Express Gen 4 doubles the bandwidth of PCIe Gen 3, speeding up data transfer from processor memory for resource-intensive tasks such as AI, data processing and working with 3D graphics.

Thanks to the ultra-fast GDDR6 memory, scientists, engineers and data science specialists get the necessary resources for processing large data sets and modeling.

GPU RTX^™ 2080 Ti

RTX 2080 Ti graphics cards are based on the powerful Turing architecture and a completely new RTX hardware ray tracing platform. Each accelerator has 544 tensor cores, 4352 CUDA cores, and 11 GB of memory.

GPU Tesla^® T4

Tesla® T4 with tensor and RT cores is the one of most advanced and energy-efficient graphics accelerator for deep learning of neural networks and inference, video transcoding, streaming, and remote desktops.

Each accelerator has 320 tensor cores, 2560 CUDA cores, and 16 GB of memory.

T4 graphics accelerators are ideal for operating neural network models in a production environment (inferencing), speech processing, and NLP.

In addition to tensor cores, T4 has RT cores that perform hardware ray tracing (retrace).

GPU Tesla^® V100

Tesla® V100 with tensor cores is the world's most technically advanced GPU for data centers.

Each graphics accelerator has 640 tensor cores, 5120 CUDA cores, and 32 GB of HBM2 memory with a maximum throughput of 900 GB/s.

The total computing performance of the server is 28 TFLOPS with double precision and 448 TFLOPS with mixed-precision and tensor cores.

V100 accelerators are ideal for training deep neural networks.

Pre-installed images

Create virtual machines based on any of the pre-installed operating systems with the necessary set of additional software. View all the pre-installed images in the Marketplace.