Dell Enterprise Hub

Documentation

Comprehensive guides and documentation to help you start and utilize our platform.

dell-ai quickstart

dell-ai is the official open-source Python SDK and command-line interface for Dell Enterprise Hub. It lets you browse validated models and platforms, generate deployment snippets, and deploy models on your local Dell system.

Install

Create a Python virtual environment and install dell-ai with uv:

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv .venv
source .venv/bin/activate
uv pip install dell-ai

You can also use pip install dell-ai inside an activated virtual environment.

Authenticate

Sign in with your Hugging Face account and confirm the active identity:

dell-ai login
dell-ai whoami

Your Hugging Face token must have access to the model you want to deploy. Gated models also require accepting the model author's access conditions on the Hugging Face Hub.

Learn more about Huggingface Hub authentication and gated models in the Dell Enterprise Hub FAQ section.

Find a model and platform

Browse the catalog:

dell-ai models list --format table
dell-ai platforms list --format table

Inspect a model and see which Dell platforms support it:

dell-ai models show google/gemma-3-27b-it
dell-ai models compatible-platforms google/gemma-3-27b-it --format table

Deploy

Choose a model, compatible platform, engine, and GPU count:

dell-ai models deploy \
    --model-id google/gemma-3-27b-it \
    --platform-id xe9680-nvidia-h200 \
    --engine docker \
    --gpus 8 \
    --replicas 1

The command fetches the validated Dell Enterprise Hub configuration and runs it locally. Docker deployments run in the background by default, with automatic host-port and GPU allocation.

You can generate the native command without executing it by replacing deploy with get-snippet:

dell-ai models get-snippet \
    --model-id google/gemma-3-27b-it \
    --platform-id xe9680-nvidia-h200 \
    --engine docker \
    --gpus 8 \
    --replicas 1

Check and remove deployments 

dell-ai status
dell-ai models undeploy -d google/gemma-3-27b-it

The deployment ID appears in the output from dell-ai status. When the same model is deployed more than once, later deployments receive a numeric suffix.

Next steps