Product Overview
NVIDIA DGX Spark is a compact desktop AI computing system built around the NVIDIA GB10 Grace Blackwell Superchip. The system combines a Blackwell-generation GPU with a 20-core Arm CPU consisting of ten Cortex-X925 cores and ten Cortex-A725 cores. It provides 128GB of coherent LPDDR5x unified system memory, allowing the CPU and GPU to work with a large shared memory pool for artificial-intelligence development and other accelerated workloads.
This configuration includes 4TB of self-encrypting NVMe M.2 storage and runs NVIDIA DGX OS. NVIDIA specifies theoretical AI performance of up to 1 PFLOP at FP4 precision under supported conditions. Connectivity includes four USB-C connections, HDMI 2.1a, 10 Gigabit Ethernet, ConnectX-7 networking, Wi-Fi 7, and Bluetooth 5.4. The compact system measures approximately 150 by 150 by 50.5 millimeters and weighs approximately 1.2 kilograms. DGX Spark is designed for local AI model development, inference, data science, prototyping, and related accelerated computing workflows. This exact DGX Spark configuration is independently identified by UPC 810152850299.
Product Information
Identification
| Field | Value |
|---|---|
| Brand | NVIDIA |
| Manufacturer | NVIDIA |
| Category | AI Desktop Computer |
| Model | DGX Spark |
| UPC | 810152850299 |
Physical
| Field | Value |
|---|---|
| Dimensions | Approximately 150 x 150 x 50.5 mm |
| Weight | Approximately 1.2 kg |
| Form Factor | Compact desktop |
Product Identifier Summary
The product name and UPC identify the NVIDIA DGX Spark desktop AI system in this configuration.
Common Uses
DGX Spark is used for local artificial-intelligence development, model inference, data science, prototyping, machine-learning experimentation, robotics development, and accelerated computing.
Maintenance & Care
Maintain adequate airflow around the system and keep ventilation openings free of dust. Install software and firmware updates according to NVIDIA guidance.
Safety Information
Use the supplied or compatible power equipment and maintain appropriate airflow. Disconnect power before servicing external connections and protect the unit from liquid exposure and excessive heat.
Technical Specifications
| Specification | Value |
|---|---|
| Architecture | NVIDIA Grace Blackwell |
| Processor | 20-core Arm CPU |
| CPU Core Configuration | 10 Cortex-X925 + 10 Cortex-A725 |
| System Memory | 128GB LPDDR5x unified memory |
| Memory Bandwidth | 273 GB/s |
| Storage | 4TB NVMe M.2 |
| AI Performance | Up to 1 PFLOP FP4 theoretical |
| USB | 4 USB-C connections |
| Ethernet | 10 GbE |
| Wireless | Wi-Fi 7 and Bluetooth 5.4 |
| Operating System | NVIDIA DGX OS |
Product History
DGX Spark was introduced as a compact personal AI computing platform built around NVIDIA’s GB10 Grace Blackwell architecture.
Key Features
- NVIDIA GB10 Grace Blackwell Superchip
- 128GB coherent unified memory
- 4TB NVMe storage
- Up to 1 PFLOP FP4 theoretical AI performance
- Wi-Fi 7 and 10 GbE networking
- Compact desktop form factor
Package Contents
The retail system includes the NVIDIA DGX Spark computer and its standard power equipment and documentation.
Compatibility
Compatibility depends on operating-system support, NVIDIA software requirements, networking infrastructure, displays, USB peripherals, and intended AI frameworks.
FAQs
How much system memory is included?
The system provides 128GB of coherent LPDDR5x unified memory.
How much storage is included?
This configuration provides 4TB of NVMe M.2 storage.
Does DGX Spark support Wi-Fi?
Yes. Wi-Fi 7 connectivity is supported.
Buying Considerations
AI workload requirements, memory capacity, model size, software compatibility, networking requirements, storage needs, and peripheral requirements should be evaluated.
Customer Feedback Summary
Public discussion commonly focuses on the compact form factor, large unified-memory pool, local AI development capabilities, and access to the NVIDIA software ecosystem. Workload suitability depends strongly on model size, precision, software optimization, and expected performance.
Related Products
Related products include GPU workstations, NVIDIA DGX systems, high-speed networking equipment, external storage, monitors, and AI-development peripherals.
Last Updated
September 2026
iGiftcardz is an independent product information website. We provide original product research, specifications, compatibility information, model numbers, and buying guides based on publicly available information. iGiftcardz is not affiliated with, endorsed by, sponsored by, or associated with any manufacturer, retailer, or marketplace unless expressly stated. Product names, trademarks, and brand names are the property of their respective owners and are used solely for identification and reference purposes.
Review this product
-
Review this product