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.

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

The ultimate deskside AI supercomputer powered by NVIDIA Grace Blackwell.

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

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

Try these developer quickstarts

Run OpenClaw in an OpenShell sandbox on DGX Station with Ollama (Nemotron)

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

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

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

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

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

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

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

Run OpenClaw in an NVIDIA OpenShell sandbox on DGX Station

Today