Bazzite AI¶

Bazzite AI OS¶

Linux OS image built on Bazzite:

• Atomic updates with instant rollback
• KDE Plasma desktop environment
• 450+ pre-installed Dev & ML packages
• Full GPU support (NVIDIA RTX 20+, AMD, Intel)
• ujust convenience commands

Deployment methods: Rebase from Bazzite KDE, QEMU virtual machine with cloud-init.

Bazzite Pods¶

OCI container images for AI/ML development:

• Docker & Podman - Linux, macOS, Windows
• Podman Quadlets - Systemd services with auto-start
• NVIDIA Container Toolkit - GPU passthrough
• Dev Containers - VS Code, GitHub Codespaces, JetBrains IDEs
• Kubernetes - AWS EKS, Google GKE, Azure AKS, on-prem
• HPC Clusters - SLURM via Apptainer

7 pre-built variants for ML/AI, DevOps, browser automation, and more.

Quick Start¶

rpm-ostree rebase ostree-image-signed:docker://ghcr.io/atrawog/bazzite-ai:stable
systemctl reboot

# Download QCOW2 image (stable)
curl -LO https://r2.bazzite.ai/qcow2/bazzite-ai-stable.qcow2

# On Bazzite AI OS: add and start VM
ujust vm add                  # Uses stable by default
ujust vm download testing     # Or download testing branch
ujust vm start bazzite-ai

# ML Development
docker run -it --rm --gpus all -v $(pwd):/workspace \
  ghcr.io/atrawog/bazzite-ai-pod-nvidia-python:stable

# JupyterLab
docker run -it --rm --gpus all -p 8888:8888 -v $(pwd):/workspace \
  ghcr.io/atrawog/bazzite-ai-pod-jupyter:stable

apiVersion: batch/v1
kind: Job
metadata:
  name: pytorch-job
spec:
  template:
    spec:
      containers:
      - name: pytorch
        image: ghcr.io/atrawog/bazzite-ai-pod-nvidia-python:stable
        resources:
          limits:
            nvidia.com/gpu: 1
      restartPolicy: OnFailure

apptainer pull docker://ghcr.io/atrawog/bazzite-ai-pod-nvidia-python:stable
srun --gres=gpu:1 apptainer exec --nv bazzite-ai-pod-nvidia-python_stable.sif bash

# Open project in VS Code, then:
# Command Palette → "Dev Containers: Reopen in Container"
# Select: jupyter, devops, base, or githubrunner

# Create quadlet file, then enable as systemd service
systemctl --user enable --now jupyter
# Access at http://localhost:8888

Core Pods¶

See all 6 pod variants →

Architecture¶

graph TB
    subgraph os["Bazzite AI OS"]
        direction TB
        fedora[Fedora 43 Atomic]
        ublue[Universal Blue]
        bazzite_base[Bazzite NVIDIA Open]
        bazzite_ai[Bazzite AI<br/>450+ Dev Packages]

        fedora --> ublue --> bazzite_base --> bazzite_ai
    end

    subgraph pods["Bazzite Pods"]
        direction TB
        base[pod-base<br/>Fedora 43 + Dev Tools]

        base --> nvidia[pod-nvidia<br/>CUDA + cuDNN]
        base --> sandbox[pod-sandbox<br/>AI + DevOps Tools]
        base --> runner[pod-githubrunner<br/>CI/CD Runner]

        nvidia --> python[pod-nvidia-python<br/>PyTorch ML]
        python --> jupyter[pod-jupyter<br/>JupyterLab]
    end

    subgraph deploy["Deployment Methods"]
        bazzite_os[Bazzite AI OS<br/>Rebase / QEMU]
        docker[Docker / Podman]
        devcontainer[Dev Containers]
        quadlet[Podman Quadlets]
        k8s[Kubernetes]
        hpc[HPC / Apptainer]
    end

    os --> bazzite_os
    pods --> docker
    pods --> devcontainer
    pods --> quadlet
    pods --> k8s
    pods --> hpc
    pods --> bazzite_os

    style bazzite_ai fill:#4CAF50,color:#fff
    style python fill:#4CAF50,color:#fff
    style jupyter fill:#4CAF50,color:#fff
    style sandbox fill:#4CAF50,color:#fff

Documentation Sections¶

Resources¶

Getting Help¶

• Report Issues: Open an issue on GitHub
• Discussions: Ask questions in GitHub Discussions