Amazon SageMaker JumpStart enables model deployment and performance evaluation

Amazon SageMaker JumpStart offers a catalog of pretrained models, allowing users to deploy models using the SageMaker Python SDK and conduct lightweight performance tests to measure latency, approximate output length, and single-request generation rate. In 2026, JumpStart introduced improvements in the Amazon SageMaker AI console, including browsing the catalog, viewing sample notebooks, and single-click deployment from Hugging Face to SageMaker AI, with pre-configured endpoint options optimized for low cost, low latency, or general-purpose workloads across generative AI models.