bretfisher/openwebui:latest

# This is a Docker Compose file for running the Open WebUI with a specific model.
# It uses the new provider feature of Compose to specify the model to be downloaded.
# Note that Open WebUI lets you select any downloaded model, but it won't auto-download them
# so the provider service will ensure it's downloaded first.
# https://docs.docker.com/compose/how-tos/model-runner/

services:
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    ports:
      - "3000:8080"
    volumes:
      - open-webui:/app/backend/data
    models:
      gemma:
        # this sets the Open WebUI envvars to use the gemma model and the model runner URL
        endpoint_var: OPENAI_API_BASE_URL
        model_var: DEFAULT_MODELS

models:
  gemma:
    model: ai/gemma3-qat:1B-Q4_K_M # Quantized. Needs 1GB of GPU memory
    # model: ai/gemma3:4B-F16 # bigger model that needs at least 8GB of GPU memory  
    # https://hub.docker.com/r/ai/gemma3
    context_size: 33000

volumes:
  open-webui: