Posted On: May 18, 2023

Starting today, the Amazon Elastic Compute Cloud (Amazon EC2) G5 instances powered by NVIDIA A10G Tensor Core GPUs are now generally available in the Local Zones location in Los Angeles. G5 instances can be used for a wide range of graphics intensive and machine learning use cases. These instances are designed for graphics-intensive applications, machine learning inference, and deliver higher performance for training simple to moderately complex machine learning models when compared to Amazon EC2 G4dn instances.

G5 instances feature up to 8 NVIDIA A10G Tensor Core GPUs and 2nd generation AMD EPYC processors. They also support up to 192 vCPUs, up to 100 Gbps of network bandwidth, and up to 7.6 TB of local NVMe SSD storage. With access to NVIDIA’s Tesla drivers for compute workloads, GRID drivers to provision RTX Virtual Workstations, and Gaming drivers at no additional cost, customers can easily optimize the G5 instances for their workloads.

Los Angeles Local Zones customers can now use Amazon EC2 G5 instances for graphics-intensive applications such as running virtual workstations, video rendering, and cloud gaming to produce high fidelity graphics in real time. Machine learning customers can use the G5 instances for high performance and cost-efficient training and inference for natural language processing, computer vision, and recommender engine use cases. Customers can purchase G5 instances as On-Demand Instances, or as part of Savings Plans.

To get started, you can enable AWS Los Angeles Local Zones from the Zones tab in Settings of the Amazon Elastic Compute Cloud (EC2) console, or ModifyAvailabilityZoneGroup API, and deploy G5 resources in us-west-2-lax-1a. To learn more, visit the G5 instance page and AWS Local Zones webpage.