⌘KCtrl+K

Start Building on DGX Spark

Find instructions and examples to run AI workloads on the NVIDIA GB10 Grace Blackwell Superchip

Your Privacy Choices

Copyright © 2026 NVIDIA Corporation

Connect from Another Computer

Get started with NVIDIA Sync

Set Up Local Network Access

Set Up Local Network Access

NVIDIA Sync helps set up and configure SSH access

5 min

DGX Spark Support

Access documentation, software, and expert assistance for your DGX Spark.

First Time Here?

Try these developer quickstarts

NemoClaw with Nemotron 3 Super and Telegram on DGX Spark30 MINS

Install NemoClaw on DGX Spark with local Ollama inference and Telegram bot integration

DGX Dashboard30 MIN

Monitor your DGX system and launch JupyterLab

Open WebUI with Ollama15 MIN

Install Open WebUI and use Ollama to chat with models on your Spark

Comfy UI45 MIN

Install and use Comfy UI to generate images

See More Playbooks Below

All Playbooks

Detailed instructions to set up and run popular AI workflows on DGX Spark

15 MIN

Single-cell RNA Sequencing

An end-to-end GPU-powered workflow for scRNA-seq using RAPIDS

3mo

20 MIN

Portfolio Optimization

GPU-Accelerated portfolio optimization using cuOpt and cuML

3mo

30 MIN

CUDA-X Data Science

Install and use NVIDIA cuML and NVIDIA cuDF to accelerate UMAP, HDBSCAN, pandas and more with zero code changes

6mo

30 MIN

Text to Knowledge Graph

Transform unstructured text into interactive knowledge graphs with LLM inference and graph visualization

6mo

2 HRS

Optimized JAX

Optimize JAX to run on Spark

6mo

LLaMA Factory

Install and fine-tune models with LLaMA Factory

6mo

Fine-tune with Pytorch

Use Pytorch to fine-tune models locally

6mo

1 HR

FLUX.1 Dreambooth LoRA Fine-tuning

Fine-tune FLUX.1-dev 12B model using Dreambooth LoRA for custom image generation

Image Generation

6mo

1 HR

Fine-tune with NeMo

Use NVIDIA NeMo to fine-tune models locally

6mo

1 HR

Unsloth on DGX Spark

Optimized fine-tuning with Unsloth

6mo

LM Studio on DGX Spark

Deploy LM Studio and serve LLMs on a Spark device; use LM Link to access models remotely.

2mo

30 MIN

Nemotron-3-Nano with llama.cpp

Run Nemotron-3-Nano-30B model using llama.cpp on DGX Spark

4mo

30 MIN

SGLang for Inference

Install and use SGLang on DGX Spark

4mo

30 MIN

NIM on Spark

Deploy a NIM on Spark

6mo

1 HR

TRT LLM for Inference

Install and use TensorRT-LLM on DGX Spark

6mo

1 HR

NVFP4 Quantization

Quantize a model to NVFP4 to run on Spark using TensorRT Model Optimizer

6mo

1 HR

Multi-modal Inference

Setup multi-modal inference with TensorRT

6mo

5 MIN

VS Code

Install and use VS Code locally or remotely

6mo

30 MIN

RAG Application in AI Workbench

Install and use AI Workbench to clone and run a reproducible RAG application

6mo

30 MIN

Set up Tailscale on Your Spark

Use Tailscale to connect to your Spark on your home network no matter where you are

6mo

Connect Two Sparks

Connect two Spark devices and setup them up for inference and fine-tuning

6mo

Build a Video Search and Summarization (VSS) Agent

Run the VSS Blueprint on your Spark

6mo

2 HOURS

Spark & Reachy Photo Booth

AI augmented photo booth using the DGX Spark and Reachy Mini.

2mo

20 MIN

Live VLM WebUI

Real-time Vision Language Model interaction with webcam streaming

3mo

30 MIN

Install and Use Isaac Sim and Isaac Lab

Build Isaac Sim and Isaac Lab from source for Spark

3mo

30 MIN

Vibe Coding in VS Code

Use DGX Spark as a local or remote Vibe Coding assistant with Ollama and Continue

6mo

30 MIN

NCCL for Two Sparks

Install and test NCCL on two Sparks

6mo

1 HR

Build and Deploy a Multi-Agent Chatbot

Deploy a multi-agent chatbot system and chat with agents on your Spark

6mo

What's New

New and majorly updated playbooks

30 MIN

Speculative Decoding

Learn how to set up speculative decoding for fast inference on Spark

6mo

30 MINS

NemoClaw with Nemotron 3 Super and Telegram on DGX Spark

Install NemoClaw on DGX Spark with local Ollama inference and Telegram bot integration

3w

30 MIN

Run models with llama.cpp on DGX Spark

Build llama.cpp with CUDA and serve models via an OpenAI-compatible API (Gemma 4 31B IT as example)

3w

30 MIN

vLLM for Inference

Install and use vLLM on DGX Spark

1mo

Connect Three DGX Spark in a Ring Topology

Connect and set up three DGX Spark devices in a ring topology

1mo

Connect Multiple DGX Spark through a Switch

Set up a cluster of DGX Spark devices that are connected through Switch

1mo

30 MINS

Secure Long Running AI Agents with OpenShell on DGX Spark

Run OpenClaw with local models in an NVIDIA OpenShell sandbox on DGX Spark

1mo

OpenClaw 🦞

Run OpenClaw locally on DGX Spark with LM Studio or Ollama

1mo