AWS AI infrastructure with NVIDIA Blackwell: Two powerful compute solutions for the next frontier of AI
Machine Learning Blog
AWS announces two powerful AI compute solutions using NVIDIA Blackwell technology:
- P6e-GB200 UltraServers: Designed for massive AI workloads with up to 72 GPUs, 360 petaflops of compute, and 13.4 TB of GPU memory
- P6-B200 Instances: Versatile option with 8 GPUs, ideal for medium to large-scale AI training and inference
Key features include:
- Enhanced security through AWS Nitro System
- Reliable performance with Elastic Fabric Adapter
- Support for Amazon SageMaker HyperPod, Amazon EKS, and NVIDIA DGX Cloud
- Liquid cooling for P6e-GB200 UltraServers for improved efficiency
These solutions aim to provide powerful, scalable infrastructure for cutting-edge AI workloads across various industries.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Sep 9
2025
2025
Powering innovation at scale: How AWS is tackling AI infrastructure challenges
May 15
2025
2025
New Amazon EC2 P6-B200 instances powered by NVIDIA Blackwell GPUs to accelerate AI innovations
Mar 16
2026
2026
AWS and NVIDIA deepen strategic collaboration to accelerate AI from pilot to production
Apr 15
2026
2026
Accelerating physical AI with AWS and NVIDIA: building production-ready applications with simulation and real-world learning
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.