n8n tutorial: Running full AI workflows offline on NVIDIA DGX Spark
n8n blog publishes a tutorial on deploying seven local models on a single NVIDIA DGX Spark (128GB unified memory), driven by LiteLLM's single OpenAI-compatible endpoint for n8n workflows, without calling any cloud APIs.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original