[email protected]
Home > Graphics > NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
1 / 5
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock
NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock

NVIDIA DGX Spark Desktop Personal AI Supercomputing System Blackwell Architecture Mini Computer in Stock

Send Inquiry

Product Description

DGX Spark Overview
DGX Spark Detail

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
  • 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
  • 1TB or 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

Key Features & Ecosystem

Cyber Resilient Architecture

DGX Spark

Cyber Resilient Architecture for Zero Trust IT environment & operations Security is integrated into every phase of the server lifecycle, including protected supply chain and factory-to-site integrity assurance. Silicon-based root of trust anchors end-to-end boot resilience while Multi-Factor Authentication (MFA) and role-based access controls ensure trusted operations.
Autonomous Collaboration

DGX Spark

Increase efficiency and accelerate operations with autonomous collaboration The OpenManage™ systems management portfolio delivers a secure, efficient, and comprehensive solution for servers. Simplify, automate and centralize one-to-many management with the OpenManage Enterprise console and iDRAC.
Sustainability

DGX Spark

Sustainability Focus From recycled materials in our products and packaging, to thoughtful, innovative options for energy efficiency, the server portfolio is designed to make, deliver, and recycle products to help reduce the carbon footprint and lower your operation costs.
DGX Spark Deployment

DGX Spark Infrastructure

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.

The passively cooled, energy-efficient, dual-socket design fits a wide range of Tesla-Certified systems from OEM vendors and is easy to integrate into existing data center infrastructure.

Product Gallery & Design

Product Architecture View 1 Product Architecture View 2
Technical Specs Layout 1 Technical Specs Layout 2 Technical Specs Layout 3
Detail Layout Scheme 1 Detail Layout Scheme 2

Frequently Asked Questions

What product categories are available?
We supply server hardware, storage units, workstations, enterprise memory, hard disks, high-performance laptops, and desktops designed to scale with your IT infrastructure requirements.
Is customization available for these hardware configurations?
Yes, we work closely with engineering teams to customize product configurations, system configurations, memory capacities, and architectures to align perfectly with your operations.
How is product quality ensured?
All products undergo evaluation through rigorous QA and QC standards managed by senior hardware engineers, ensuring stable performance and authenticity across all systems.
Are distribution and agency opportunities open?
Yes, we actively seek distribution channels and partnerships with global agents and IT system integrators.
What type of packaging is used for shipping?
Standard shipments are packaged in heavy-duty cardboard boxes designed for secure hardware transit. Custom packaging requests can also be accommodated.
What is the average lead time for orders?
Typical delivery times average around 7 days, depending on order size and custom configuration requirements.

Related Products

Tesla L40 GDDR6 Blade Server Graphics Card for Deep Learning AI with L40S & L40N Features Stock Available

Tesla L40 GDDR6 Blade Server Graphics Card for Deep Learning AI with L40S & L40N Features Stock Available
Server Graphics Cards: RTX4090 RTX5090 Deep Computing Acceleration, DeepSeek, Deploy Server Graphics Cards TESLA L40 48G

Server Graphics Cards: RTX4090 RTX5090 Deep Computing Acceleration, DeepSeek, Deploy Server Graphics Cards TESLA L40 48G
New Spot Tesla A10 24GB GDDR6 Fan Artificial Intelligence Computational Inference Server Accelerated Graphics Card Workstation

New Spot Tesla A10 24GB GDDR6 Fan Artificial Intelligence Computational Inference Server Accelerated Graphics Card Workstation
New Spot Tesla L40 48GB GPU Deep Learning Computing Edge Computing AI Server Graphics Card

New Spot Tesla L40 48GB GPU Deep Learning Computing Edge Computing AI Server Graphics Card
New Spot Tesla L20 48GB GPU Deep Learning Computing Edge Computing AI Server Graphics Card

New Spot Tesla L20 48GB GPU Deep Learning Computing Edge Computing AI Server Graphics Card
Brand New Spot L4 24GB GPU Professional Accelerated Computing AI Virtualization Server Host Graphics Card

Brand New Spot L4 24GB GPU Professional Accelerated Computing AI Virtualization Server Host Graphics Card
Brand New Spot A40 48GB GDDR6 Fan Artificial Intelligence Large Model Training Inference Server Host

Brand New Spot A40 48GB GDDR6 Fan Artificial Intelligence Large Model Training Inference Server Host
New Spot Tesla L40S 48GB GPU Deep Learning Computing Edge Computing AI Server Graphics Card

New Spot Tesla L40S 48GB GPU Deep Learning Computing Edge Computing AI Server Graphics Card
New Spot Tesla A16 64GB GPU Deep Learning Computing Edge Computing AI Server Graphics Card Host

New Spot Tesla A16 64GB GPU Deep Learning Computing Edge Computing AI Server Graphics Card Host
Brand New Stock Tesla T4 16GB GDDR6 Fan GPU Inference Training AI Server Workstation Dedicated Acceleration Graphics Card

Brand New Stock Tesla T4 16GB GDDR6 Fan GPU Inference Training AI Server Workstation Dedicated Acceleration Graphics Card