--- title: Advancing AI model interoperability with Docker and... description: ModelPack, a CNCF project defining an open OCI-based standard for packaging and distributing AI models, has partnered with Docker to solve model... canonical: https://daily.dev/posts/advancing-ai-model-interoperability-with-docker-and-modelpack-aufsp1str twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Advancing AI model interoperability with Docker and ModelPack | daily.dev og:description: ModelPack, a CNCF project defining an open OCI-based standard for packaging and distributing AI models, has partnered with Docker to solve model... og:url: https://daily.dev/posts/advancing-ai-model-interoperability-with-docker-and-modelpack-aufsp1str og:image: https://api.daily.dev/og/posts/AuFSp1Str.png og:image:alt: Advancing AI model interoperability with Docker and ModelPack og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Advancing AI model interoperability with Docker and ModelPack **[CNCF](https://daily.dev/sources/cncf)** · 5 min read · 0 upvotes · 1 comments ## Summary ModelPack, a CNCF project defining an open OCI-based standard for packaging and distributing AI models, has partnered with Docker to solve model interoperability problems. Docker Model Runner (DMR) previously packaged models using its own proprietary OCI media types, limiting portability across tools. Following collaboration between Docker and ModelPack maintainers (including Nutanix, Ant, Jozu, and Red Hat), the ModelPack spec was hardened and Docker Model Runner now supports exporting models in ModelPack format via a new --format=cncf flag on the docker model package command. This lets models be published to any OCI-compliant registry, such as Docker Hub or Quay, and consumed by any compatible serving framework rather than being locked into Docker's tooling. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I export a Docker Model Runner model in ModelPack format? Use the --format=cncf option with the docker model package command, which produces a ModelPack-formatted OCI artifact instead of the default Docker model format. The resulting artifact can then be published to any OCI registry, such as Docker Hub or Quay, for consumption by compatible serving frameworks and tools beyond Docker's own ecosystem. _daily.dev surfaces updates like this for teams standardizing AI model packaging across tools._ ### What is the difference between the ModelPack and Docker Model Runner OCI media types? ModelPack uses application/vnd.cncf.model.manifest.v1+json as its manifest type and application/vnd.cncf.model.config.v1+json for the config descriptor, while Docker Model Runner uses application/vnd.docker.ai.model.config.v0.1+json for its config descriptor and has no equivalent artifact-type manifest. Both formats comply with OCI artifact guidelines, so OCI registries can store either regardless of type. _developers comparing AI packaging formats can track spec changes like this on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@trevorsuna** · 0 upvotes > Using OCI as the common transport makes this much more practical than another model-specific packaging island. The real win is being able to move the same artifact between registries and serving stacks. Clear compatibility tests across tools will matter as implementations multiply. ## Similar posts on daily.dev - [Private AI Coding: OpenCode \+ Model Runner](https://daily.dev/posts/private-ai-coding-opencode-model-runner-dhdneogi0) · Docker · 2 upvotes · 0 comments - [Docker Isn’t Just About Containers Anymore](https://daily.dev/posts/docker-isn-t-just-about-containers-anymore-86dkmipl5) · SD Times · 1 upvotes · 0 comments --- Tags: [#docker](https://daily.dev/tags/docker), [#cncf](https://daily.dev/tags/cncf) [View this post on daily.dev](https://daily.dev/posts/advancing-ai-model-interoperability-with-docker-and-modelpack-aufsp1str) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Advancing AI model interoperability with Docker and ModelPack","url":"https://daily.dev/posts/advancing-ai-model-interoperability-with-docker-and-modelpack-aufsp1str","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/advancing-ai-model-interoperability-with-docker-and-modelpack-aufsp1str"},"datePublished":"2026-08-12T11:05:00.024Z","dateModified":"2026-09-14T06:05:47.049Z","description":"ModelPack, a CNCF project defining an open OCI-based standard for packaging and distributing AI models, has partnered with Docker to solve model...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/073f67e0b9cfd972d1df31bf8228b2da?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/073f67e0b9cfd972d1df31bf8228b2da?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"CNCF","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"CNCF","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/55536a03390741eebd96d2f9b74d2d8d","url":"https://daily.dev/sources/cncf"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/advancing-ai-model-interoperability-with-docker-and-modelpack-aufsp1str","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"docker,cncf","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"CNCF","item":"https://daily.dev/sources/cncf"},{"@type":"ListItem","position":3,"name":"Advancing AI model interoperability with Docker and ModelPack"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/advancing-ai-model-interoperability-with-docker-and-modelpack-aufsp1str","comment":[{"@type":"Comment","text":"Using OCI as the common transport makes this much more practical than another model-specific packaging island. The real win is being able to move the same artifact between registries and serving stacks. Clear compatibility tests across tools will matter as implementations multiply.","datePublished":"2026-08-13T02:40:31.714Z","url":"https://daily.dev/posts/AuFSp1Str#c-QAnxjaYVt","author":{"@type":"Person","name":"Trevor Suna","url":"https://daily.dev/trevorsuna","image":"https://media.daily.dev/image/upload/s--dZ7gXxpp--/f_auto/v1784081551/avatars/avatar_EMoP47rpuw8DNjhp6R1b6?_a=BAMAMicg0"}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/advancing-ai-model-interoperability-with-docker-and-modelpack-aufsp1str#faq","mainEntity":[{"@type":"Question","name":"How do I export a Docker Model Runner model in ModelPack format?","acceptedAnswer":{"@type":"Answer","text":"Use the --format=cncf option with the docker model package command, which produces a ModelPack-formatted OCI artifact instead of the default Docker model format. The resulting artifact can then be published to any OCI registry, such as Docker Hub or Quay, for consumption by compatible serving frameworks and tools beyond Docker's own ecosystem. daily.dev surfaces updates like this for teams standardizing AI model packaging across tools."}},{"@type":"Question","name":"What is the difference between the ModelPack and Docker Model Runner OCI media types?","acceptedAnswer":{"@type":"Answer","text":"ModelPack uses application/vnd.cncf.model.manifest.v1+json as its manifest type and application/vnd.cncf.model.config.v1+json for the config descriptor, while Docker Model Runner uses application/vnd.docker.ai.model.config.v0.1+json for its config descriptor and has no equivalent artifact-type manifest. Both formats comply with OCI artifact guidelines, so OCI registries can store either regardless of type. developers comparing AI packaging formats can track spec changes like this on daily.dev."}}]} ```