Skip to content
Welcome to our store

Start typing to find products

Looking for something? Try searching by category, product name, or brand.

Your cart is empty

Continue shopping
Skip to product info

The NVIDIA® DGX™ Spark (940-54242-0000-000) is a compact yet powerful AI computing platform designed to accelerate next-generation AI development and deployment. Powered by the advanced NVIDIA GB10 Grace Blackwell Superchip, it delivers up to one petaFLOP of AI performance in an energy-efficient form factor, making it ideal for developers, researchers, and enterprise AI applications.

Equipped with 128GB of high-speed memory and the preinstalled NVIDIA AI software stack, DGX Spark enables seamless prototyping, fine-tuning, and inference of modern reasoning and generative AI models with up to 200 billion parameters. Optimized for large language models, deep learning, robotics, and edge AI workloads, it provides a powerful local AI development environment for cutting-edge innovation.

 


Features

  • NVIDIA GB10 Grace Blackwell Superchip: Powered by the advanced NVIDIA GB10 Grace Blackwell architecture, the system delivers up to 1 petaFLOP of AI computing performance at FP4 precision for demanding AI and generative workloads.
  • 128GB Unified System Memory: Equipped with 128GB of high-speed coherent unified memory, enabling seamless AI development, testing, fine-tuning, and inference for models with up to 200 billion parameters directly from your desktop environment.
  • NVIDIA ConnectX™ High-Speed Networking: Integrated NVIDIA ConnectX™ networking allows multiple NVIDIA DGX Spark systems to be connected together, supporting larger AI workloads and enabling processing of models with up to 405 billion parameters.
  • NVIDIA AI Software Ecosystem: Comes with the complete NVIDIA AI software stack, including optimized frameworks, libraries, development tools, and NVIDIA NIM microservices for accelerated generative AI, deep learning, and enterprise AI deployment.


Specifications

 

Architecture

NVIDIA Grace Blackwell

GPU NVIDIA Blackwell Architecture
CPU

20 core Arm, 10 Cortex-X925

+ 10 Cortex-A725 Arm

CUDA Cores NVIDIA Blackwell Generation
Tensor Cores 5th Generation
RT Cores 4th Generation
Tensor Performance (Theoretical FP4 TOPS using the sparsity feature) 1 PFLOP
System Memory

128 GB LPDDR5x, coherent unified system memory

Memory Interface 256-bit
Memory Bandwidth Up to 273 GB/s
Storage 4 TB NVME.M2 with self-encryption
USB 4x USB TypeC
Ethernet

1x RJ-45 connector

10 GbE

NIC ConnectX-7 NIC @ 200 Gbps
Wi-Fi WiFi 7
Bluetooth BT 5.4 w/LE
Audio-output HDMI multichannel audio output
Power Supply 240W
Display Connectors 1x HDMI 2.1a
NVENC | NVDEC 1x | 1x
OS NVIDIA DGX™ OS
System Dimensions 150 mm L x 150 mm W x 50.5 mm H
System Weight 1.2 kg

 

Application

  • Prototyping
  • Fine-Tuning
  • Inference
  • Data Science
  • Edge Applications


Part List

  1. Quick Start Guide x1
  2. Power Supply x1
  3. Power Cord


Documents

NVIDIA® DGX™ Spark (940-54242-0000-000)

SKU: ROBO15

Designed to accelerate intelligent machines with real-time AI processing.

Regular price
Rs. 381,360.84 INR

Delivery within 48 Hours

Request a Quote for Bulk Orders

Click here to fill the details

The NVIDIA® DGX™ Spark (940-54242-0000-000) is a compact yet powerful AI computing platform designed to accelerate next-generation AI development and deployment. Powered by the advanced NVIDIA GB10 Grace Blackwell Superchip, it delivers up to one petaFLOP of AI performance in an energy-efficient form factor, making it ideal for developers, researchers, and enterprise AI applications.

Equipped with 128GB of high-speed memory and the preinstalled NVIDIA AI software stack, DGX Spark enables seamless prototyping, fine-tuning, and inference of modern reasoning and generative AI models with up to 200 billion parameters. Optimized for large language models, deep learning, robotics, and edge AI workloads, it provides a powerful local AI development environment for cutting-edge innovation.

 


Features

  • NVIDIA GB10 Grace Blackwell Superchip: Powered by the advanced NVIDIA GB10 Grace Blackwell architecture, the system delivers up to 1 petaFLOP of AI computing performance at FP4 precision for demanding AI and generative workloads.
  • 128GB Unified System Memory: Equipped with 128GB of high-speed coherent unified memory, enabling seamless AI development, testing, fine-tuning, and inference for models with up to 200 billion parameters directly from your desktop environment.
  • NVIDIA ConnectX™ High-Speed Networking: Integrated NVIDIA ConnectX™ networking allows multiple NVIDIA DGX Spark systems to be connected together, supporting larger AI workloads and enabling processing of models with up to 405 billion parameters.
  • NVIDIA AI Software Ecosystem: Comes with the complete NVIDIA AI software stack, including optimized frameworks, libraries, development tools, and NVIDIA NIM microservices for accelerated generative AI, deep learning, and enterprise AI deployment.


Specifications

 

Architecture

NVIDIA Grace Blackwell

GPU NVIDIA Blackwell Architecture
CPU

20 core Arm, 10 Cortex-X925

+ 10 Cortex-A725 Arm

CUDA Cores NVIDIA Blackwell Generation
Tensor Cores 5th Generation
RT Cores 4th Generation
Tensor Performance (Theoretical FP4 TOPS using the sparsity feature) 1 PFLOP
System Memory

128 GB LPDDR5x, coherent unified system memory

Memory Interface 256-bit
Memory Bandwidth Up to 273 GB/s
Storage 4 TB NVME.M2 with self-encryption
USB 4x USB TypeC
Ethernet

1x RJ-45 connector

10 GbE

NIC ConnectX-7 NIC @ 200 Gbps
Wi-Fi WiFi 7
Bluetooth BT 5.4 w/LE
Audio-output HDMI multichannel audio output
Power Supply 240W
Display Connectors 1x HDMI 2.1a
NVENC | NVDEC 1x | 1x
OS NVIDIA DGX™ OS
System Dimensions 150 mm L x 150 mm W x 50.5 mm H
System Weight 1.2 kg

 

Application

  • Prototyping
  • Fine-Tuning
  • Inference
  • Data Science
  • Edge Applications


Part List

  1. Quick Start Guide x1
  2. Power Supply x1
  3. Power Cord


Documents