GPU-3070 Instances^NEW

GPU
NVIDIA GPU
Processor
AMD EPYC™ 7003 Series
Processor Frequency
2.65 GHz
GPU Memory
8GB GDDR6
Memory
16 GB
Memory type
DDR4
Bandwidth
2.5 Gbps
Storage
Block Storage on demand

Available regions

fr-par-2
Green AZ

Fully dedicated GPU
Best performance/price ratio
Integrated with Scaleway ecosystem

From€0.85^{ex. VAT/Hour}

Launch your GPU Instance now !

Launch your GPU-3070 instance

Unbeatable price/performance ratio

The new GPU-3070 offer will be up to 40% more powerful and 21% less expensive than Render-S, helping you discover new horizons.

Many complementary cloud services

Take advantage of Block Storage and our S3 compatible Object Storage, easily orchestrate your Kubernetes containers with Kubernetes Kapsule for no extra-charge, and store your images in our fully managed Container Registry.

Using Sustainable GPU

GPU-3070 is built on a high-end, energy-efficient graphic card in fr-par-2 – our sustainable, adiabatic datacenter which makes your GPU usage more eco-friendly.

Outstanding features for your GPU-3070

High-end specifications

Included

We paired one of the best processors – AMD EPYC™ 7003 Series with a world-class universal GPU for your intensive workload.

Your own dedicated GPU

Included

Scaleway GPU-3070 Instances come with your own dedicated GPU powered by CUDA.

Kubernetes-ready ecosystem

Included

Deploy your Kubernetes nodes simply and easily with Kubernetes Kapsule, or accelerate your Docker containers with the NVIDIA Container Toolkit to save valuable time.

Scaleway ecosystem integration

Included

Make your life easier by leveraging the Scaleway cloud services ecosystem with our Block Storage, Object Storage, Container Registry, and Kubernetes Kapsule.

Private Networks

Included

Private Networks is compatible with GPU Instances at no extra cost. Privates Networks enables you to create your own layer-2 private networks between your Development Instances, General Purpose Instances and GPU Instances.

Learn more

API, CLI & SDK

Included

We designed a suite of tools to support developers in the deployment, configuration, orchestration and automation of infrastructures, whatever their size and type. Your infrastructure can be managed with our API and SDKs, using Terraform or with the scw command-line interface (CLI). You can also configure your instance immediately with cloud-init.

24/7 support tickets

We ensure your services are always up and running. Our technical assistance is available 24 hours a day, 7 days a week to answer all your questions and to assist you. Simply open a new ticket in case of a problem. You can also reach our support directly by phone or get faster responses if you upgrade your support plan.

Discover more use cases with our GPU-Render Instance powered by NVIDIA Tesla P100 16GB PCIe.

Get started with GPU !

Get started with our GPU tutorials

How to create and manage a GPU Instance

Discover the Tutorial

Quick and simple GPU acceleration

Our Universal GPU 3070 Instances are built to supercharge your GPU workloads, whether you need one or several standalone GPU Instances, such as Jupyter Notebook, or want to deploy a Kubernetes cluster.