AIHardwareCloudProduct Release
Run Local AI Agents with Faster Models and Multi-Node Clustering on NVIDIA DGX Spark
NVIDIA introduces solutions for running autonomous AI agents locally using faster models and multi-node clustering on DGX Spark, addressing compute demands and privacy concerns.
The rise of autonomous, long-running AI agents has introduced a new class of compute demand, namely tasks that maintain large context windows, spawn concurrent subagents, and iterate continuously without cloud dependency. Security and privacy concerns are also accelerating the shift toward local agents. Developers can now run autonomous agents on hardware they own with NVIDIA NemoClaw and take advantage of faster models and multi-node clustering on NVIDIA DGX Spark to handle these compute-intensive tasks efficiently.