Dell DGX GB10 128G Advanced Enhanced Running Memory Large Storage Space SSD Big Data AI Processing Workstation

Product Description

DGX Spark Interface
DGX Spark Overview
Technical Specifications
System Architecture * Chipset: GB10 Grace Blackwell Superchip
* Combines a 20-core Arm CPU with a Blackwell GPU via NVLink-C2C interconnect
* Coherent unified memory architecture for CPU-GPU data sharing
CPU 20-core Arm v9 processor
* 10× Cortex-X925 cores (high-performance)
* 10× Cortex-A725 cores (energy-efficient)
GPU Blackwell architecture with:
* 6,144 CUDA cores (equivalent to RTX 5070)
* 5th-generation Tensor Cores (1,000 AI TOPS FP4 precision)
* 4th-generation RT Cores (ray tracing acceleration)
Video Engines 1× NVENC (9th gen), 1× NVDEC (5th gen)
System Memory 28GB LPDDR5X unified memory
* 256-bit interface, 273GB/s bandwidth
* Supports models up to 200B parameters locally, 405B parameters with dual-node clustering
Storage 4TB NVMe M.2 SSD (self-encrypting)
Networking * ConnectX-7 Smart NIC (200Gbps RDMA for clustering)
* 10GbE RJ45 port
* Wi-Fi 7 (802.11be) + Bluetooth 5.3
Interfaces * 4× USB4 Type-C (40Gbps)
* 1× HDMI 2.1a (supports 8K video output)
* Audio: HDMI multichannel audio
Power Consumption * 170W typical operation
* Up to 224W peak under heavy load
Cooling Passive airflow design optimized for silent operation
Physical Specifications * Dimensions: 150mm (L) × 150mm (W) × 50.5mm (H)
* Weight: 1.2kg
* Form Factor: FHFL dual-slot (rack-mountable with optional kit)
Operating System DGX OS (Ubuntu 22.04-based)
* Pre-installed AI Enterprise software stack
* Supports frameworks: PyTorch, TensorFlow, RAPIDS
Model Capabilities * Inference: Up to 200B parameters (e.g., LLaMA 2, DeepSeek-R1)
* Fine-tuning: Up to 70B parameters
* Distributed training: Scale to 405B parameters with dual DGX Spark nodes
Security * Secure Boot and ECC memory protection
* Confidential computing with ARM TrustZone
Development Tools * AI Enterprise Suite (cuDNN, TensorRT, etc.)
* NGC container registry access
Core Advantages
🛡️

Cyber Resilient Architecture

Security is integrated into every phase of the lifecycle, including protected supply chain and factory-to-site integrity assurance. Silicon-based root of trust anchors end-to-end boot resilience.

⚙️

Autonomous Collaboration

Increase efficiency and accelerate operations with comprehensive management solutions. Simplify, automate and centralize management with professional consoles and controllers.

🌱

Sustainability

Designed to reduce carbon footprint and lower operation costs through innovative energy efficiency options and recycled materials in packaging.

DGX Spark Deployment

Enterprise-Grade Performance

Designed for 24x7 enterprise data center operations, it features enterprise-grade components and energy-efficient hardware optimized for deployment at scale.

Supports Secure Boot with Hardware Root of Trust technology, provides an extra layer of security, and meets NEBS Level 3 standards to meet new data center standards.

Product Display
Hardware Image 1
Hardware Image 2
Hardware Image 3
Hardware Image 4
Hardware Image 5
Hardware Image 6
Frequently Asked Questions
What models can the DGX Spark handle?
It supports inference for models up to 200B parameters (e.g., LLaMA 2, DeepSeek-R1) and fine-tuning up to 70B parameters. It can scale to 405B parameters via dual-node clustering.
What are the key components of the system architecture?
The system utilizes the GB10 Grace Blackwell Superchip, combining a 20-core Arm CPU with a Blackwell GPU featuring 6,144 CUDA cores and 5th-gen Tensor Cores.
Is the system suitable for silent office environments?
Yes, it features a passive airflow design specifically optimized for silent operation, making it suitable for both data centers and quiet workspaces.
What connectivity options are available for high-speed networking?
The unit includes a ConnectX-7 Smart NIC supporting 200Gbps RDMA for clustering, a 10GbE RJ45 port, and Wi-Fi 7 (802.11be) support.
Which operating system and AI frameworks are supported?
It runs DGX OS (Ubuntu 22.04-based) and comes pre-installed with the AI Enterprise software stack, supporting PyTorch, TensorFlow, and RAPIDS.
What are the physical dimensions and power requirements?
The unit is compact at 150mm x 150mm x 50.5mm, weighing 1.2kg. It typically operates at 170W, with a peak load of up to 224W.

Related Products