Skip to content

Bazzite AI

An immutable Linux distribution and OCI container ecosystem for AI/ML development.

What is Bazzite AI?

Bazzite AI combines:

  • Immutable OS - Fedora Atomic Desktop with 450+ pre-installed dev tools
  • AI/ML Workloads - Ready-to-run containers for Ollama, JupyterLab, ComfyUI, and more
  • GPU Support - NVIDIA, AMD, and Intel GPUs with automatic detection
  • Run Anywhere - Workloads run on any platform with Docker/Podman

Quick Start

Step Command Description
1 Install Bazzite AI OS Rebase from Bazzite KDE
2 ujust config gpu setup Setup GPU containers
3 ujust ollama start Run your first workload
# Run Ollama with GPU
docker run -d --gpus all -p 11434:11434 \
  -v ~/.ollama:/home/jovian/.ollama \
  ghcr.io/atrawog/bazzite-ai-pod-ollama:stable

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

Available Workloads

Workload Description Quick Start
Ollama LLM inference server ujust ollama start
JupyterLab Interactive notebooks ujust jupyter start
ComfyUI AI image generation ujust comfyui start
nvidia-python ML/AI development ujust apptainer shell
Open WebUI Chat interface ujust openwebui start
FiftyOne Dataset visualization ujust fiftyone start

View all workloads →

Deployment Options

Platform Best For
Bazzite AI OS Full experience with ujust commands
Docker & Podman Any platform with containers
Kubernetes Cluster deployments
HPC & Apptainer Research clusters with SLURM
Dev Containers VS Code / IDE integration

View all deployment options →

GPU Support

All workloads support GPU acceleration:

Vendor Support Notes
NVIDIA Yes RTX 20+ with CUDA
AMD Yes RX 5000+ via ROCm
Intel Yes Gen 7+ / Arc via Vulkan

GPU Setup Guide →

Architecture

Bazzite AI combines an immutable OS with containerized workloads:

Getting Started

  1. Requirements - Hardware and storage
  2. Installation - Install Bazzite AI OS
  3. GPU Setup - Configure GPU containers
  4. Choose a Workload - Start using AI tools

See Also