AWS has launched EC2 P6-B300 instances powered by NVIDIA Blackwell Ultra B300 GPUs, featuring 8 GPUs with 2.1 TB GPU memory, 6.4 Tbps EFA networking, and 4 TB system memory. These instances offer 2x networking bandwidth, 1.5x GPU memory, and 1.5x GPU TFLOPS compared to P6-B200 instances, optimized for training and deploying trillion-parameter foundation models and LLMs. Available in US West (Oregon) through EC2 Capacity Blocks for ML and Savings Plans.
Sort: