Linode GPU Instances

On-demand GPUs for parallel processing workloads such as machine learning, scientific computing, and video processing.

Linode GPU Instances give you access to enterprise-grade graphical processors tailored specifically for compute, graphics, and data-intensive use cases. Powered by NVIDIA Quadro RTX 6000 GPUs, Linode GPUs allow you to harness the power of CUDA, Tensor, and RT cores for parallel processing, deep learning, and ray tracing workloads with the same ease as Linode CPUs.

GPUs are currently available to customers as a part of a paid pilot. To learn more about available plans and pricing click here. If you are interested in getting started with GPUs today, you can find more information in the Cloud Manager or create your account.

This is a limited release pilot so resources may not be readily available. If you would like to be notified when more GPU instances and additional plan types are available, add your information here.

Quadro RTX 6000 Specs

CUDA Cores (Parallel-Processing) 4,608
Tensor Cores (Machine & Deep Learning) 576
RT Cores (Ray Tracing) 72
GPU Memory 24 GB GDDR6
Rays Cast 10 Giga Rays/Sec
FP32 Performance 16.3 TFLOPS
Features & Graphics

On-demand GPU

Between purchasing, installing, and maintaining GPUs, the cost of ownership is often very high. Linode GPUs allow you to leverage the power of GPUs while benefiting from the main value proposition of cloud: turning a CapEx into an OpEx.

Simplifying Complex Use Cases

You focus on your core competencies, we'll worry about the hardware that makes them possible. Linode GPUs remove the barrier to entry to complex use cases such as machine learning, AI, and video streaming.

Market Leading Hardware

Linode GPUs are NVIDIA Quadro RTX 6000 units, currently considered one of the best in market GPUs. With CUDA, Tensor, and RT cores in each unit, these GPUs support any use cases associated with parallel processing, deep learning, or ray tracing.

Multiple Plan Types

One GPU card isn't enough for your projected workloads? Not a problem. Linode GPU plan types offer up to four cards per instance, depending on how much horsepower you need.

Use Cases

Machine Learning

Leverage powerful open source software such as TensorFlow to get started with machine learning. Deep learning and AI workloads are also supported.

Video Processing

Get the most out of the G in your GPU. 4K / 8K high-definition live streaming, video rendering, media encoding, and other graphics related use cases are supported in a few easy steps.

High Performance Computing (HPC)

Compute and data intensive workloads for industries such as Financial Services, Healthcare / Life Sciences, media, and more are a cinch with GPU instances.

Linode GPU Instance plans start at $1000 / mo.

View all plans here

Get started with Linode GPU Instances today!