Powered by NVIDIA H100 Tensor Core GPUs, P5.48xl instances deliver up to four times faster results and reduce training costs by up to 40% compared to previous GPU-based EC2 generations. These capabilities accelerate machine learning tasks such as training large language models and diffusion models essential to generative AI applications.
Targeted use cases include question answering, code and content generation, and speech recognition. These instances embed into SageMaker notebook instances to facilitate development in JupyterLab and CodeEditor environments, with AWS guidance available for configuration and use.
Source & further reading
Announcing Region Expansion of P5.48xl instances on SageMaker Notebook Instances ↗Source published 2026-05-27. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.