DigestAI news desk

Cut through the AI noise.

Hardware & Compute4 min read

NVIDIA launches DGX Spark 64GB with 100-billion-parameter model support

The system features the GB10 Grace Blackwell Superchip, DGX OS, and full NVIDIA AI software stack, supporting up to 100-billion-parameter models locally. Two units can cluster via NVIDIA Sync Cluster Assistant to pool memory to 128GB and support up to 200-billion-parameter models, delivering up to 1.7x performance in Qwen 3.8 27B tests. The platform includes NVIDIA Agent Toolkit, CUDA-X AI…

4 sources primary source

What you can do with it

AI at Work →
DGX Spark 64GB by NVIDIA

Provides a complete local AI platform with unified memory and software stack for agents.

What you get You can run AI agents around the clock.

Who for
marketers
Cost
paid from $4999
Effort
minutes

Use it for

  • Run AI agents around the clock
  • Power AI apps on everyday PCs
  • Scale workloads by clustering units

How to set it up · From the article

  1. Download a supported inference framework like Ollama or vLLM
  2. Download the recommended local model for your workflow
  3. Connect two units via ConnectX-7 ports and launch NVIDIA Sync Cluster Assistant to scale

Watch out Requires compatible hardware from partner manufacturers

Key points from the news

  • DGX Spark 64GB starts at $4,999 and is available from Acer, ASUS, Dell, Gigabyte, HP and MSI on October 23, 2026
  • Supports up to 100-billion-parameter models on a single unit and up to 200 billion when two units are clustered
  • Two clustered 64GB systems deliver up to 1.7x performance in NVIDIA's Qwen 3.8 27B test
Full story from NVIDIA Blog · by Allen Bourgoyne primary sourceOpen source ↗

NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI

NVIDIA Blog · 2 October 2026

Loading the full article…

This text was published by NVIDIA Blog and written by Allen Bourgoyne. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

4sources
Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Hardware & Compute

All →

Related stories