Docker Model Runner: Run AI Models Locally with Full Control | Docker

Secure, minimal container images for every team, free with enterprise features, if needed.
Explore a curated catalog of open-source AI models on Docker Hub or pull directly from Hugging Face.
Run LLMs locally and take full ownership of your AI workflows and data privacy.
Maximize performance on your local machine with fast, efficient inference.
Send inference requests via OpenAI’s API, perfect for fast, scalable app integration.
Use with popular Docker tools, including Docker Compose, Testcontainers, and Offload for easy scaling from local to CI/CD.
Package, manage, and share models to any OCI-compliant registry such as Docker Hub.
Securely manage access and control for your models as OCI-artifacts in Docker Hub.
Connect with frameworks such as Spring AI, LangChain, OpenWebUI, and more using the Docker tooling you already know and trust.
Discover curated AI models on Docker Hub.
Try Docker Model Runner and bring AI development into your local workflow
Get started with a comprehensive, step-by-step quick guide.
Explore the newest features and watch a hands-on demo on publishing models.