Skip to main content
NVIDIA
Explore
Models
Skills
Blueprints
GPUs
Docs
Help Center
Getting Started
  1. Create and verify your account to unlock full access to NVIDIA NIM APIs.
ResourcesDeveloper ForumsContact Support
FAQs
  • Terms of Use
    Privacy Policy
    Your Privacy Choices
    Contact

    Copyright © 2026 NVIDIA Corporation

    Start Building AI on DGX Station

    Find examples to run the most powerful AI workloads on NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

    Stay informed about DGX Station

    The ultimate deskside AI supercomputer powered by NVIDIA Grace Blackwell.

    Learn More

    Enterprise-Grade Agentic AI At Your Desk

    Data center performance at your desk

    Run NemoClaw with a Local LLM

    Run NemoClaw with a Local LLM

    Build a local AI assistant in an OpenShell sandbox with vLLM inference and optional Telegram

    Install Now

    Develop Powerful AI Workflows

    Experience The World's Most Powerful Local AI Supercomputer

    DGX Station AI Skills and dgx-assist15 MIN

    Inspect DGX Station software and route version-aware, CLI-backed workflows

    Serve LLMs with vLLM30 MIN

    High-throughput serving for 30+ models, with continuous batching and an OpenAI-compatible API

    Generate Images and Videos with ComfyUI45 MIN

    Node-based diffusion workflows for images and videos with FLUX, Wan, HunyuanVideo, and Stable Diffusion

    Isaac GR00T N1.6 Fine-Tuning45 MIN

    Fine-tune and benchmark NVIDIA's GR00T N1.6 robotics foundation model on DGX Station

    See More Playbooks Below

    What's New

    New and majorly updated playbooks

    • DGX Station
      60 MIN

      Connect Two DGX Stations for Distributed Workloads

      Combined memory and compute over a direct high-speed link
      • Station
      • DGX Station
      • NCCL
      • Multi-Node
      Last updated on July 20, 2026
    • DGX Station
      30 MIN

      Run NemoClaw with a Local LLM

      Build a local AI assistant in an OpenShell sandbox with vLLM inference and optional Telegram
      • Station
      • vLLM
      • Telegram
      • DGX Spark
      • Agentic Workflow
      • NemoClaw
      • DGX Station
      • OpenClaw
      • OpenShell
      • Spark
      Last updated on August 6, 2026

    Explore Playbooks

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

    • DGX Station
      30 MIN

      Build Knowledge Graphs with txt2kg

      Extract triples with Ollama or vLLM, store them in a graph database, and explore them in a GPU-accelerated web UI
      • vLLM
      • DGX Spark
      • Ollama
      • DGX Station
      • Application
      Last updated on August 6, 2026
    • DGX Station
      45 MIN

      Topic Modeling

      Extract insights from massive text datasets using cuML's GPU-accelerated BERTopic
      • Data Science
      • Station
      • NLP
      • BERTopic
      • Machine Learning
      • cuML
      Last updated on March 9, 2026
    • DGX Station
      12 HOURS

      Train a Chat Model with NanoChat

      Build a ChatGPT-style LLM end-to-end — tokenizer, pretraining, SFT — then chat via web UI or CLI
      • PyTorch
      • Docker
      • DGX Station
      • Application
      Last updated on August 4, 2026
    • DGX Station
      30 MIN

      NVFP4 Pretraining with Megatron Bridge

      Pretrain Llama 3.1 8B with NVFP4 mixed precision on DGX Station using Megatron Bridge
      • Training
      • Station
      • NVFP4
      • Megatron Bridge
      Last updated on May 27, 2026
    • DGX Station
      30 MIN

      Serve LLMs with vLLM

      High-throughput serving for 30+ models, with continuous batching and an OpenAI-compatible API
      • Station
      • vLLM
      • DGX Spark
      • RTX
      • DGX Station
      • Inference
      • Spark
      • RTX PRO
      Last updated on August 6, 2026
    • DGX Station
      30 MIN

      Serve LLMs with SGLang

      High-throughput serving with RadixAttention, structured output, and an OpenAI-compatible API
      • DGX Spark
      • DGX Station
      • Inference
      • SGLang
      Last updated on August 4, 2026
    • DGX Station
      45 MIN

      Generate Images and Videos with ComfyUI

      Node-based diffusion workflows for images and videos with FLUX, Wan, HunyuanVideo, and Stable Diffusion
      • Image Generation
      • Content Creation
      • ComfyUI
      • Docker
      • DGX Spark
      • DGX Station
      Last updated on August 4, 2026
    • DGX Station
      45 MIN

      Isaac GR00T N1.6 Fine-Tuning

      Fine-tune and benchmark NVIDIA's GR00T N1.6 robotics foundation model on DGX Station
      • Station
      • Fine-Tuning
      • Isaac GR00T
      • Blackwell
      • DGX Station
      • VLA
      • Robotics
      • GB300
      Last updated on May 26, 2026
    • DGX Station
      15 MIN

      MIG on DGX Station

      Enable and configure Multi-Instance GPU (MIG) on DGX Station with GB300 Ultra (B300 GPUs)
      • Station
      • System Configuration
      • DGX Station
      • MIG
      • GPU Partitioning
      • B300
      • GB300
      Last updated on March 5, 2026
    • DGX Station
      5 MIN

      Register DGX Station to Brev

      Link your DGX Station to Brev for remote access and sharing
      • Station
      • DGX Station
      • Brev
      Last updated on May 30, 2026
    • DGX Station
      60 MIN

      Quantize Models to NVFP4 with NVIDIA Model Optimizer

      Cut memory ~3.5× vs FP16 while keeping accuracy close to FP8, then validate with an OpenAI-compatible endpoint
      • Station
      • vLLM
      • DGX Spark
      • Model Optimizer
      • DGX Station
      • TensorRT-LLM
      • Inference
      • Spark
      Last updated on August 4, 2026
    • DGX Station
      15 MIN

      DGX Station AI Skills and dgx-assist

      Inspect DGX Station software and route version-aware, CLI-backed workflows
      • vLLM
      • AI Agents
      • Blackwell
      • DGX Station
      • MIG
      • Cursor
      • SGLang
      • Gemini CLI
      • Codex
      • dgx-assist
      • Station
      • AGENTS.md
      • Claude Code
      • Agent Skills
      • Mixed Coherency
      • GB300
      Last updated on May 30, 2026
    • DGX Station
      30 MIN

      Run NemoClaw with a Local LLM

      Build a local AI assistant in an OpenShell sandbox with vLLM inference and optional Telegram
      • Station
      • vLLM
      • Telegram
      • DGX Spark
      • Agentic Workflow
      • NemoClaw
      • DGX Station
      • OpenClaw
      • OpenShell
      • Spark
      Last updated on August 6, 2026
    • DGX Station
      30 MIN

      Secure AI Agents with OpenShell

      Isolate OpenClaw with kernel-level policies and route inference to a local model
      • Station
      • vLLM
      • DGX Spark
      • Docker
      • Agentic Workflow
      • DGX Station
      • OpenClaw
      • OpenShell
      • Spark
      Last updated on August 6, 2026
    • DGX Station
      30 MINS

      Local Coding Agent

      Run local CLI coding agents with Claude Code and Ollama on DGX Station (NVIDIA GB300) using qwen3.6:27b
      • Station
      • Coding
      • Ollama
      • Claude Code
      • DGX Station
      • LLM
      • GB300
      Last updated on March 25, 2026
    • DGX Station
      60 MIN

      Local Healthcare Agent on DGX Station

      Run healthcare AI agents that analyze patient data and predict protein structures in an OpenShell sandbox on DGX Station
      • Station
      • OpenFold3
      • NemoClaw
      • Nemotron
      • DGX Station
      • OpenShell
      • Healthcare
      • FHIR
      • AI Agent
      • GB300
      Last updated on May 15, 2026
    • DGX Station
      2 HRS

      Profiler-Driven Kernel Optimization for Fine-Tuning

      Use torch.profiler to find training bottlenecks, then write custom Triton kernels to optimize LLaMA 8B fine-tuning
      • Training
      • Station
      • Fine-Tuning
      • Performance Optimization
      • Kernel Development
      • DGX Station
      • LLaMA
      • Triton
      • GB300
      Last updated on May 26, 2026