Skip to content

Docker & Podman Deployment

Run Bazzite AI workloads on any platform with Docker or Podman.

Bazzite AI OS Users

If you're on Bazzite AI OS, use the ujust commands instead for integrated GPU support and systemd service management.

Quick Start

Workload Image Description
nvidia-python ghcr.io/atrawog/bazzite-ai-pod-nvidia-python:stable ML/AI development
jupyter ghcr.io/atrawog/bazzite-ai-pod-jupyter:stable JupyterLab
ollama ghcr.io/atrawog/bazzite-ai-pod-ollama:stable LLM inference
comfyui ghcr.io/atrawog/bazzite-ai-pod-comfyui:stable Image generation 
# NVIDIA GPU
docker run -it --rm --gpus all -v $(pwd):/workspace \
  ghcr.io/atrawog/bazzite-ai-pod-nvidia-python:stable

# CPU-only (macOS/Windows/Linux without GPU)
docker run -it --rm -v $(pwd):/workspace \
  ghcr.io/atrawog/bazzite-ai-pod-nvidia-python:stable

# AMD/Intel GPU (Linux)
docker run -it --rm --device=/dev/dri -v $(pwd):/workspace \
  ghcr.io/atrawog/bazzite-ai-pod-nvidia-python:stable

Workload Examples

nvidia-python (ML/AI)

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

# Run training script
docker run --rm --gpus all -v $(pwd):/workspace \
  ghcr.io/atrawog/bazzite-ai-pod-nvidia-python:stable \
  pixi run --manifest-path /opt/pixi/pixi.toml python /workspace/train.py

jupyter (JupyterLab)

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

# Different port
docker run -it --rm --gpus all -p 9999:8888 -v $(pwd):/workspace \
  ghcr.io/atrawog/bazzite-ai-pod-jupyter:stable

ollama (LLM Inference)

# Start Ollama server
docker run -d --gpus all -p 11434:11434 \
  -v ~/.ollama:/home/jovian/.ollama \
  ghcr.io/atrawog/bazzite-ai-pod-ollama:stable

# Pull and run a model
curl http://localhost:11434/api/pull -d '{"name": "llama3.2"}'
curl http://localhost:11434/api/generate -d '{"model": "llama3.2", "prompt": "Hello"}'

Common Options

GPU Access

GPU Flag
NVIDIA (all) --gpus all
NVIDIA (specific) --gpus '"device=0"'
AMD/Intel --device=/dev/dri

Volume Mounts

Mount Purpose
-v $(pwd):/workspace Working directory
-v ~/.ollama:/home/jovian/.ollama Ollama models

Ports

Service Port
JupyterLab -p 8888:8888
Ollama -p 11434:11434
ComfyUI -p 8188:8188

Prerequisites

Docker

Podman

NVIDIA GPU (Linux only)

# Ubuntu/Debian
sudo apt-get install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

# Fedora/RHEL
sudo dnf install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

Troubleshooting

GPU Not Detected

# Verify GPU on host
nvidia-smi

# Check container toolkit
docker run --rm --gpus all nvidia/cuda:12.0-base nvidia-smi

Permission Denied

Container runs as user jovian (UID 1000):

# Fix host directory permissions
chmod 755 ./my-project

See Also