Amazon EC2 G7e instances now available in Asia Pacific (Tokyo) region

Amazon EC2 G7e Instances Now Available in Asia Pacific (Tokyo) Region
Amazon EC2 G7e instances, accelerated by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, are now available in the Asia Pacific (Tokyo) region. These instances offer up to 2.3x inference performance compared to G6e instances and are ideal for deploying large language models, agentic AI models, multimodal generative AI models, and physical AI models.
Key features include:
- Up to 8 GPUs: Each instance can feature up to 8 NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs.
- High Memory: Each GPU has 96 GB of memory.
- High Performance: Up to 192 vCPUs and 1600 Gbps of networking bandwidth.
- Advanced GPU Support: Includes support for NVIDIA GPUDirect Peer to Peer (P2P) and RDMA with EFA in EC2 UltraClusters.
What to do
- Visit the AWS Management Console, AWS CLI, or use AWS SDKs to get started.
- Learn more about G7e instances.
Source: AWS release notes
If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.



