⌘KCtrl+K

Your Privacy Choices

Copyright © 2026 NVIDIA Corporation

Start Building on DGX Station

Find instructions and examples to run AI workloads on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip

Stay informed about DGX Station

The ultimate deskside AI supercomputer powered by NVIDIA Grace Blackwell.

Maximize GPU Utilization with MIG

Split GPUs into smaller instances for efficient multi-model inference and development.

MIG on DGX Station

MIG on DGX Station

Enable and configure Multi-Instance GPU (MIG) on DGX Station with GB300 Ultra (B300 GPUs)

Explore Playbooks

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

30 MIN

Text to Knowledge Graph on DGX Station

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

2mo

45 MIN

Topic Modeling

Extract insights from massive text datasets using cuML's GPU-accelerated BERTopic

2mo

30 MIN

Nanochat Training

Train a small ChatGPT-style LLM (nanochat) with tokenizer, pretraining, midtraining, and SFT on DGX Station with GB300 Ultra

2mo

20 MIN

Serve Qwen3-235B with vLLM

Set up vLLM server with Qwen3-235B on DGX Station

2mo

15 MIN

MIG on DGX Station

Enable and configure Multi-Instance GPU (MIG) on DGX Station with GB300 Ultra (B300 GPUs)

2mo

1 HR

NVFP4 Quantization

Quantize a model to NVFP4 to run on DGX Station using TensorRT Model Optimizer

2mo

30 MINS

NemoClaw with Nemotron-3-Super and vLLM on DGX Station

Install NemoClaw on DGX Station with local vLLM inference and Telegram bot integration

2w

30 MINS

Secure Long Running AI Agents with OpenShell on DGX Station

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

2mo

30 MINS

Local Coding Agent

Run local CLI coding agents with Ollama on DGX Station (NVIDIA GB300) using glm-4.7-flash (fast) or unsloth/GLM-4.7-GGUF:Q8_0 (best quality)

1mo

Get Started on GB300

Try these developer quickstarts

NemoClaw with Nemotron-3-Super and vLLM on DGX Station30 MINS

Install NemoClaw on DGX Station with local vLLM inference and Telegram bot integration

Serve Qwen3-235B with vLLM20 MIN

Set up vLLM server with Qwen3-235B on DGX Station

NVFP4 Quantization1 HR

Quantize a model to NVFP4 to run on DGX Station using TensorRT Model Optimizer

Local Coding Agent30 MINS

Run local CLI coding agents with Ollama on DGX Station (NVIDIA GB300) using glm-4.7-flash (fast) or unsloth/GLM-4.7-GGUF:Q8_0 (best quality)

See More Playbooks Below