> Markdown version of [/videos/1593-bootable-ai-containers-with-podman-desktop?t=447](https://www.wearedevelopers.com/videos/1593-bootable-ai-containers-with-podman-desktop?t=447). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Bootable AI Containers with Podman Desktop

Configuration drift ruins AI deployments. Eliminate dependency headaches by treating your entire operating system as a reproducible artifact. Learn to build bootable AI containers using Podman Desktop.

- **Speakers:** [Cedric Clyburn](https://www.wearedevelopers.com/@cedric-clyburn), [Kevin Dubois](https://www.wearedevelopers.com/@kevin-dubois)
- **Event:** World Congress 2025
- **Published:** August 20, 2025
- **Duration:** 29:19
- **URL:** https://www.wearedevelopers.com/videos/1593-bootable-ai-containers-with-podman-desktop

## Summary

Traditional infrastructure management often struggles with configuration drift, inconsistent environments, and manual patching across disparate servers. Just as application containers revolutionized software delivery by introducing immutable, standardized packages, bootable containers apply this same OCI-compliant logic directly to operating systems. By bundling a Linux kernel along with OS base utilities inside a standard `Containerfile`, teams can treat their entire operating system as a reproducible artifact. This paradigm shift unifies the deployment lifecycle, allowing developers to provision edge devices, virtual machines, and bare metal servers with the exact same tools and processes used to manage application microservices.

At the core of this modern infrastructure workflow is `bootc`, an underlying utility that enables a running system to seamlessly pull transactional updates directly from a container registry—and easily roll back if an update fails. This hyper-declarative deployment strategy solves persistent challenges in AI and machine learning workloads, where complex Python dependencies and framework mismatches frequently cause deployment friction. By bundling everything from the kernel to the Large Language Model (LLM) and VLLM inference server into a single versioned image, organizations can run models as close to the hardware as possible. This approach drastically reduces latency, accelerates AI inference, and eliminates the typical dependency headaches associated with complex AI application stacks.

Bridging the gap from local development to production deployment is Podman Desktop, a CNCF-backed, open-source alternative to Docker Desktop. Utilizing the AI Lab extension, developers can locally provision and test containerized code assistants or RAG applications running open-weight models. Once validated, developers can use the bootc-image-builder extension to effortlessly export their AI container into standardized disk files such as QCOW2, ISO, or AMI. Ultimately, this workflow proves that compiling an operating system customized for an AI workload is now as straightforward as executing a basic `podman build`, ensuring complete environment parity from the local developer laptop out to the production edge.

**Keywords:** bootable containers, podman desktop, immutable operating systems, bootc system management, oci compliant images, configuration drift mitigation, bare metal server deployment, edge device provisioning, localized ai inference, python dependency resolution, llm environment configuration, systemd container integration, cncf open source projects, container deployment pipelines, hypervisor disk image conversion

## Chapters

1. **Introduction and CNCF open source tool donations** (00:05) — An overview of the session schedule and the donation of container-native tools to the CNCF.
1. **Evolving from application containers to bootable systems** (02:38) — How the principles of application containers address infrastructure configuration drift by creating immutable operating systems.
1. **Building and updating system images with Bootc** (07:27) — Using standard tooling to compile operating systems via container files and deploying continuous updates with Bootc.
1. **Optimizing AI deployments with bootable containers** (13:00) — Packaging models close to the hardware to improve inference times and manage Python dependencies effectively.
1. **Managing containerized infrastructure with Podman Desktop** (15:41) — Utilizing open source GUI tools to build container images and export them directly into specific disk formats.
1. **Developing a containerized AI code assistant locally** (17:22) — Running localized AI development workflows using extensions and containerized inference servers.
1. **Converting AI applications into bootable OS disk images** (22:33) — Compiling the code assistant app, model container, and system dependencies into a bare metal deployable image file.

## Related Moments

- [Managing operating systems as containers with bootc](https://www.wearedevelopers.com/videos/1600-develop-on-windows-deploy-on-red-hat-enterprise-linux) (from "Develop on Windows, Deploy on Red Hat Enterprise Linux")
- [Building local containerized models with Podman AI Lab](https://www.wearedevelopers.com/videos/950-supercharge-your-cloud-native-applications-with-generative-ai) (from "Supercharge your cloud-native applications with Generative AI")
- [Building native Linux systems using standard container files](https://www.wearedevelopers.com/videos/1608-simplifying-edge-app-delivery-one-workflow-thousands-of-devices) (from "Simplifying edge app delivery: one workflow, thousands of devices")
- [Running an AI model locally using Podman AI Lab](https://www.wearedevelopers.com/videos/1597-self-hosted-llms-from-zero-to-inference) (from "Self-Hosted LLMs: From Zero to Inference")
- [Addressing local development challenges with Podman Desktop](https://www.wearedevelopers.com/videos/1133-containers-and-kubernetes-made-easy-deep-dive-into-podman-desktop-and-new-ai-capabilities) (from "Containers and Kubernetes made easy: Deep dive into Podman Desktop and new AI capabilities")
- [Creating bootable operating systems with the bootc project](https://www.wearedevelopers.com/videos/1610-enterprise-linux-as-container-images) (from "Enterprise Linux as Container Images")

## Related Articles

- [Building AI Solutions with Rust and Docker](https://www.wearedevelopers.com/magazine/494-building-ai-solutions-with-rust-and-docker)
- [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere)
- [How we Build The Software of Tomorrow](https://www.wearedevelopers.com/magazine/120-how-we-build-the-software-of-tomorrow)
- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)

## Related Jobs

- [Devops Engineer](https://www.wearedevelopers.com/jobs/ext/1940926-devops-engineer) at **Bitpanda**
- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [Cloud Foundations Team](https://www.wearedevelopers.com/jobs/ext/1483289-cloud-foundations-team) at **GitHub**
- [DevOps Engineer (m/f/d)](https://www.wearedevelopers.com/jobs/48303-devops-engineer-m-f-d) at **basebox GmbH**
- [Senior Engineer, Infrastructure Platform](https://www.wearedevelopers.com/jobs/ext/328836-senior-engineer-infrastructure-platform) at **Intercom, Inc.**