Skip to content
Live
Trending storyPast story

NVIDIA DGX Spark supports cross-node AI model execution

2 reports2 outlets27 days agoUpdate

The story so far

AI overview

NVIDIA has launched DGX Spark, supporting the parallel running of cutting-edge AI models across 8 nodes, requiring hundreds of GB of memory; developers can orchestrate multiple models and perform chained inference. Previously, NVIDIA stated that the design goal of DGX Spark was to bring AI development to the desktop, and now it can connect more nodes. NVIDIA showcased its full lineup of local AI hardware at GTC Berlin, including RTX Spark, DGX Spark, and DGX Station, to assist in the development of next-generation intelligent agents.

AI-written from the reports · Updated 27 days ago

Developments

2 developments

  1. 23 Oct, 00:00 · 1 reports
    Running cutting-edge AI models
    NVIDIA Technical Blog:Running Frontier-Class AI Models Across 8 NVIDIA DGX Spark Nodes
  2. 21 Oct, 18:50 · 1 reports
    Bringing the Spark to Europe: Local Intelligence Powers Next
    NVIDIA Blog:Bringing the Spark to Europe: Local Intelligence Powers Next Wave of Agents

Coverage timeline

Follow the coverage to see every side of the story.

23 Oct
  1. NVIDIA Technical Blog
    Running Frontier-Class AI Models Across 8 NVIDIA DGX Spark Nodes

    NVIDIA DGX Spark can connect more nodes, support parallel running of cutting-edge AI models, requiring hundreds of GB of memory; developers can orchestrate multiple models and perform chained inference.

21 Oct
  1. NVIDIA Blog
    Bringing the Spark to Europe: Local Intelligence Powers Next Wave of Agents

    NVIDIA showcased its full lineup of local AI hardware at GTC Berlin, with RTX Spark now available to support personal agents on Windows PCs, DGX Spark enabling developers to build and scale Linux applications, and DGX Station designed for Linux enterprise teams to run cutting-edge workloads, with the Windows version launching in December.