SourceAmazon EC2 P6-B300 instances are now available in the Asia Pacific (Seoul) Region
Users in the Seoul region can train and deploy trillion-parameter AI models faster due to increased memory and networking bandwidth.
- Provides 8 NVIDIA Blackwell Ultra GPUs with 2.1 TB high bandwidth GPU memory
- Features 6.4 Tbps EFA networking, 300 Gbps dedicated ENA throughput, and 4 TB system memory
- Delivers 2x networking bandwidth, 1.5x GPU memory size, and 1.5x GPU TFLOPS compared to P6-B200 instances
- Available in p6-b300.48xlarge size across US West (Oregon), AWS GovCloud (US-East), US East (N. Virginia), and Asia Pacific (Seoul) regions