NVIDIA Launches RTX Spark Compact Desktops for Local AI Workloads

Executive Briefing
“NVIDIA and hardware partners have launched RTX Spark compact desktops featuring Grace...”
Key Takeaways
- 1.New RTX Spark compact desktops from ASUS, Dell, and MSI are available today.
- 2.These systems feature a 20-core NVIDIA Grace CPU, a Blackwell RTX GPU with 6,144 CUDA cores, and up to 128GB of unified memory.
- 3.This hardware supports running massive 120-billion-parameter large language models locally.
NVIDIA and hardware partners have launched RTX Spark compact desktops featuring Grace processors and Blackwell RTX GPUs to support local artificial intelligence workloads. These systems provide a dedicated Windows environment for running large models and automated tasks directly on the device.
Product Features & Key Highlights
New RTX Spark compact desktops from ASUS, Dell, and MSI are available today.
These systems feature a 20-core NVIDIA Grace CPU, a Blackwell RTX GPU with 6,144 CUDA cores, and up to 128GB of unified memory.
This hardware supports running massive 120-billion-parameter large language models locally.
Practical Assessment & Evaluation
Integrating robust hardware with high unified memory helps resolve resource constraints when executing complex language models directly on personal devices.
Local processing solutions help users maintain code and file security while eliminating per-token cloud API charges.
Pricing, Availability & Next Steps
The real-world performance and power consumption of the system while maintaining continuous AI tasks in office environments have not been independently evaluated.
Specific retail pricing for each configuration from various hardware partners has not been detailed.







