sagemaker/pr_2709/en/tutorials/index.md

# Tutorials

Pick the offering that matches how you want to work. Every tutorial is self-contained and reproducible.

| Offering | Use it when | Start here |
|---|---|---|
| SageMaker SDK | You want full control from Python: deploy any Hub model, run custom training on managed infrastructure. | [Quickstart](./sagemaker-sdk/sagemaker-sdk-quickstart) |
| JumpStart | You want a curated model catalog with performant defaults, deployable in a few clicks. | [Quickstart](./jumpstart/jumpstart-quickstart) |
| Bedrock | You want JumpStart models behind the managed Bedrock APIs (Agents, Knowledge Bases, Guardrails). | [Quickstart](./bedrock/bedrock-quickstart) |
| EC2, ECS, and EKS | You want to run the Deep Learning Containers directly on AWS compute services. | [Quickstart](./compute-services/compute-services-quickstart) |
| Inference Endpoints | You want Hugging Face to manage the infrastructure, optimized for cost and throughput. | [Guide](https://huggingface.co/docs/inference-endpoints/guides/create_endpoint) |

All offerings run the same Hugging Face [Deep Learning Containers](../get-started/dlcs). For end-to-end recipes (TRL fine-tuning, embedding models, Inferentia2, and more), see the **Examples** section in the sidebar.