NVIDIA DGX Spark Clusters Can Now Scale to Eight Systems and 1TB of Unified Memory

NVIDIA Expands DGX Spark Clusters to Eight Systems With One Terabyte of Unified Memory

Eight systems can run Z.ai's 753-billion-parameter GLM 5.3 model, and benchmark results vary by model and network layout.

Nvidia will let eight DGX Spark computers pool 1TB of memory for local AI

Nvidia has announced support for connecting eight DGX Spark systems into a cluster with 1TB of combined unified memory. The larger configuration is intended to run AI models locally that would not fit on a smaller group of the desktop computers. There is still a setup milestone ahead: Nvidia says eight-node support in its Sync ... Nvidia will let eight DGX Spark computers pool 1TB of memory for local AI The post Nvidia will let eight DGX Spark c…

Nvidia DGX Spark Clusters Now Reach 8 Units and 1 TB of Memory

Nvidia has just given its local AI DGX Spark systems a pretty strong boost, focusing on both the processing power and the memory capacity that developers have in their day-to-day work. The most eye-catching news is that DGX Spark units now allow clusters of up to eight machines, raising the unified memory up to a …

NVIDIA expands DGX Spark clusters to eight nodes for local AI

NVIDIA says DGX Spark now supports eight-node clusters, lifting unified memory to 1TB and improving throughput for local AI workloads. (Read More)

NVIDIA DGX Spark Clusters Can Now Scale to Eight Systems and 1TB of Unified Memory

NVIDIA says its DGX Spark compact AI systems can now be linked in manual configurations of up to eight units. The company’s announcement at GTC Berlin describes the change as a way to give developers more memory capacity for larger local AI workloads, longer context windows and multiple simultaneous sessions.