Skip to content

Quick Start

Terminal window
# Install uv if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install sparkrun and set up your cluster
uvx sparkrun setup

The setup wizard walks you through cluster creation, SSH mesh, and CX7 networking interactively. See the Setup Wizard Walkthrough for a detailed step-by-step guide.

Use the cluster created by the wizard as your default. A single-node cluster is normal; for larger installations, put all nodes in the default and optionally add smaller logical groups. See Recommended Cluster Setups. Replace mylab below with the name you chose in the wizard.

Terminal window
sparkrun cluster set-default mylab

Let Sparkrun choose placement within the default cluster:

Terminal window
sparkrun run qwen3-1.7b-vllm
# Or select a different saved cluster
sparkrun run qwen3-1.7b-vllm --cluster mylab

sparkrun launches detached containers, follows startup logs, and returns after readiness and required hooks. Use --no-follow to wait quietly, --follow to keep watching after readiness, or --no-ready-wait for launch-only completion. Ctrl+C detaches the observers and leaves the detached workload running. See run.

With a cluster configured, scale across multiple DGX Sparks:

Terminal window
sparkrun run qwen3-1.7b-vllm --tp 2

Each DGX Spark has one GPU with 128 GB unified memory, so --tp 2 splits the model across 2 nodes. See Multi-Node Tensor Parallelism for a full walkthrough.

Terminal window
sparkrun show nemotron3-nano-30b-nvfp4-vllm

This displays recipe details and a memory estimate. Unknown or lower-bound estimates do not establish fit; account for runtime allocation, KV cache, and observed host capacity. See Memory-aware fit.

The following output is illustrative; job IDs, addresses, images, and durations vary.

Terminal window
# Check what's running
$ sparkrun status
Job: @sparkrun-transitional/qwen3-1.7b-llama-cpp [e0ed758410a2] (1 container(s))
solo 10.24.11.13 (ib: 192.168.11.13) Up 45 minutes ghcr.io/spark-arena/dgx-llama-cpp:latest
logs: sparkrun logs e0ed758410a2
stop: sparkrun stop e0ed758410a2
Terminal window
# Re-attach to logs (Ctrl+C is always safe) -- you can reference recipe or job ID
sparkrun logs @sparkrun-transitional/qwen3-1.7b-llama-cpp
# Stop a workload (shown here using job ID for unambiguous reference)
sparkrun stop e0ed758410a2

Spark Arena is the community hub for DGX Spark recipe benchmarks — browse benchmark results, then run them directly with sparkrun.

Official Recipes are maintained by the Spark Arena team and hosted on GitHub. They are tested and optimized for NVIDIA DGX Spark systems.

Community Recipes are contributed by the community and hosted on GitHub.