Serve LLMs with vLLM

Step 1
Identify your configuration

Choose the configuration that matches the hardware you will use:

Configuration	How vLLM will run
One DGX Spark	On the GB10 GPU in one device
One DGX Station	On the GB300 GPU in one device
Two DGX Sparks	Across one GB10 GPU in each device

If you are unsure which NVIDIA GPU is available, connect to the device with NVIDIA Sync, open Terminal, and run:

Bash

nvidia-smi --query-gpu=name --format=csv,noheader

Step 2
Use the recommended recipe

Select the row for your configuration. These recipes were chosen to provide reasoning and tool calling while making effective use of the available hardware.

Configuration	Recommended model	Why this recipe	Continue with
One DGX Spark	Qwen3.8-27B NVFP4	The quantized model fits one Spark and has a hardware-specific vLLM configuration.	Single device
One DGX Station	Qwen3.8-Flash-Next NVFP4	The larger mixture-of-experts model takes advantage of the Station's greater memory and uses a dedicated container.	Single device
Two DGX Sparks	Qwen3.8-27B NVFP4	The predefined cluster recipe uses tensor parallelism across both Sparks and adds DFlash2 speculative decoding.	Multi-node DGX Spark

The launch tabs provide the complete model, container, and serving configuration for these recommended recipes. You do not need to translate the recipe commands yourself.

Step 3
Decide whether to use another recipe

For the simplest path, keep the recommended recipe and continue to the tab shown in the table.

If you are comfortable selecting a different model, container, and launch configuration, continue to Step 4.

IMPORTANT

The copy-and-paste launch configurations in this playbook are tested for the recommended recipes. Another recipe may require different model-download, container, environment, memory, parser, or parallelism settings.

Step 4
Generate another recipe

To use another recipe:

Open the filtered recipe catalog for your hardware:
- DGX Spark recipes
- DGX Station recipes
Select a model that supports your hardware configuration.
Select the model variant and precision.
Enable the capabilities you need, such as tool calling or reasoning.
Copy the model ID, container image, environment variables, and complete vllm serve command from the generated recipe.
Keep all values from the same generated recipe. Do not combine settings from different model variants or hardware configurations.
For two-Spark serving, confirm that a matching recipe exists in spark-vllm-docker. Do not assume a single-device recipe can run across two devices.

NOTE

Model size is not the only compatibility requirement. The container architecture, vLLM version, quantization format, parsers, and parallel configuration must also match the selected model and hardware.

Step 5
Continue to the launch instructions

For a recommended one-Spark or one-Station recipe, continue with Single device.
For the recommended two-Spark recipe, continue with Multi-node DGX Spark.
For another recipe, use its generated installation and serving commands as the manual path. Substitute its settings only where the following launch instructions explicitly tell you to do so.

Serve LLMs with vLLM

Step 1Identify your configuration

Step 2Use the recommended recipe

Step 3Decide whether to use another recipe

Step 4Generate another recipe

Step 5Continue to the launch instructions

Resources

Step 1
Identify your configuration

Step 2
Use the recommended recipe

Step 3
Decide whether to use another recipe

Step 4
Generate another recipe

Step 5
Continue to the launch instructions