Introducing Amazon EC2 G4 Instances with NVIDIA T4 Tensor Core GPUs, the Most Cost-effective GPU Platform for Machine Learning Inference and Graphics Intensive Applications
Today, we are announcing that the next generation GPU powered instance family, Amazon EC2 G4 GPU instances, are generally available.
Amazon EC2 G4 instances deliver the industry’s most cost-effective GPU platform for deploying machine learning models in production and graphics-intensive applications. G4 instances provide the latest generation NVIDIA T4 Tensor Core GPUs, AWS custom second generation Intel® Xeon® Scalable (Cascade Lake) processors, up to 50 Gbps of networking throughput, and up to 900 GB of local NVMe storage. The bare metal G4 instance that is coming soon will offer 100 Gbps of networking throughput and 1.8 TB of local NVMe storage.
EC2 G4 instances are optimized for machine learning application deployments such as image classification, object detection, recommendation engines, automated speech recognition and language translation that need access to low level GPU software libraries. These instances are also cost-effective solutions for graphics-intensive applications such as remote graphics workstations, video transcoding and game streaming in the cloud. EC2 G4 instances are offered in different instance sizes with access to one GPU or multiple GPUs with different amounts of vCPU and memory to give you the flexibility to pick the right instance size for your applications.
G4 instances are available in the US East (N. Virginia and Ohio), US West (Oregon and N. California), Europe (Frankfurt, Ireland, and London), and Asia Pacific (Seoul and Tokyo) AWS Regions as On-Demand, Reserved, or Spot Instances. G4 instances are also accessible in Amazon SageMaker. To learn more about G4 instances, visit the G4 page.