Unparalleled Performance
Enable your project with unparalleled performance served by our three GPU offerings. From AI to rendering, find the best GPU for your individual project and workload.
Enable your project with unparalleled performance served by our three GPU offerings. From AI to rendering, find the best GPU for your individual project and workload.
With videos becoming ever more popular and larger in size, a GPU that helps reduce rendering time is irreplaceable. Cut your rendering times significantly by trusting in our GPUs.
Needs change, requirements change - Exoscale changes with them. Scale up your applications as needed to answer the ever-changing environments.
Exoscale’s GPU instances are ready to be used with the framework of your choice, whether it’s Tensorflow, OneClick, FFmpeg, Theano, Caffe2, or PyTorch. Optimize costs and performance with maximum computational power, on-demand.
GPUs fitting for your needs. Rely on our performance to solve your individual problem.
Our Tesla P100 based GPU1 is recommended for high-performance computing in the cloud.
DiscoverOur Tesla V100 based GPU2 is recommended for deep learning, neural networks, AI and more.
DiscoverOur A40 based GPU3 is the all-rounder for AR, VR, simulations, rendering, AI and more.
DiscoverGPU instances are available on shared dedicated hypervisors for improved isolation.
Our GPUs are based on NVIDIA GPU cards, providing you with cutting-edge bare metal performance and technology.
Integrate GPUs seamlessly with your existing infrastructure. Add parallel computational power to your stack with no effort.
All GPU offerings are billed by the second. Avoid costly surprises on your bill with our simple pay-per-use pricing.
Exoscale's GPU instances are among the most competitive offerings on the market. Save up to 75% compared to competition with our GPUs.
As a true European cloud provider, all data is stored in the country of your chosen zone, making it fully GDPR compliant.
Depending on your project and requirements, you might need a different GPU. This comparison table has an overview of the features and potential use cases for each GPU offering, giving you the right direction to go in for your next project. Contact us if you need more information about GPUs.
GPU1 | GPU2 | GPU3 | |
---|---|---|---|
Graphic Card | Tesla P100 | Tesla V100 | A40 |
Cuda Cores per card | 3584 | 5120 | 10752 |
Tensor Cores per card | 0 | 640 | 336 |
RT Cores per card | 0 | 0 | 84 |
GPU memory per card | 16 GB | 16 GB | 48 GB |
GPU cards | 1-4 | 1-4 | 1-8 |
CPU cores | 12-48 | 12-48 | 12-96 |
RAM per instance | 56-225 | 56-225 | 56-448 |
SSD local storage | max. 1.6 TB (SATA) | max. 1.6 TB (SATA) | max. 1.6 TB (NVMe) |
Zones | CH-GVA-2 | AT-VIE-1 | DE-FRA-1 |
Usable for | AI, Machine Learning, Inference | AI, Machine Learning, Inference | Video, Rendering, VDI AI, Machine Learning, Inference |
Learn more | GPU1 | GPU2 | GPU3 |
Combine the simplicity and scalability of the Exoscale Cloud with the power of NVIDIA GPUs. With our Docker based template you can access the full potential of the NVIDIA GPU Cloud (NGC) and significantly reduce time to solution.
NVIDIA GPU Cloud (NGC) provides a selected set of GPU-optimized software for artificial intelligence applications,
visualizations and HPC. The NGC Catalog includes containers, pre-trained models, Helm charts for Kubernetes deployments
and specific AI toolkits with SDKs.
NGC catalog works with both Exoscale Compute and Exoscale SKS. The image template for SKS worker nodes embeds the optimized version
of the container runtime for NVIDIA cards, making quick work of starting any application from the catalog without
fiddling with drivers and CUDA versions.
When running mission critical production workloads in the cloud, a partner you can rely on makes all the difference. Our customer success engineers have helped hundreds of customers from all over Europe migrate, run and scale production workloads on Exoscale.
Contact us