NVIDIA DGX Spark

Original price was: ₹1,099,999.00.Current price is: ₹649,999.00.

The NVIDIA DGX Spark Personal AI Supercomputer combines the GB10 Grace Blackwell Superchip, 1,000 AI TOPS (FP4), 128GB LPDDR5X unified memory, and up to 4TB NVMe SSD storage in a compact desktop system. Designed for AI developers, researchers, and enterprises, it supports PyTorch, TensorFlow, CUDA, TensorRT, and NVIDIA AI Enterprise for local LLM inference, fine-tuning, and advanced AI application development.

Compare

NVIDIA DGX Spark

Features

  • Powered by the NVIDIA GB10 Grace Blackwell Superchip.
  • Delivers up to 1,000 AI TOPS (FP4) for AI inference and development.
  • 20-core NVIDIA Grace CPU optimized for AI workloads.
  • 128GB LPDDR5X unified memory for running large AI models locally.
  • Up to 4TB NVMe SSD for high-speed storage.
  • High-speed 10 Gigabit Ethernet, Wi-Fi 7, and Bluetooth 5.3 connectivity.
  • Supports CUDA, TensorRT, cuDNN, NVIDIA AI Enterprise, and NIM Microservices.
  • Compatible with PyTorch, TensorFlow, JAX, NeMo, and other AI frameworks.
  • Compact desktop form factor with quiet active cooling.
  • Ideal for LLM inference, AI model fine-tuning, computer vision, robotics, and generative AI development.

Specifications

Product Name NVIDIA DGX Spark
Brand NVIDIA
Model DGX Spark
Product Type Personal AI Supercomputer
AI Processor NVIDIA GB10 Grace Blackwell Superchip
GPU Architecture NVIDIA Blackwell
CPU NVIDIA Grace CPU (20 Cores: 10 × Cortex-X925 + 10 × Cortex-A725)
AI Performance Up to 1,000 AI TOPS (FP4)
GPU Memory Unified Memory Architecture
System Memory 128GB LPDDR5X Unified Memory
Memory Bandwidth Up to 273 GB/s
Storage Up to 4TB NVMe SSD
Networking 10GbE Ethernet, Wi-Fi 7, Bluetooth 5.3
USB Ports USB4 Type-C
Video Output HDMI 2.1
Operating System NVIDIA DGX OS (Linux-based)
AI Software NVIDIA AI Enterprise, CUDA, TensorRT, cuDNN, NIM Microservices
Supported Frameworks PyTorch, TensorFlow, JAX, NVIDIA NeMo, RAPIDS
Power Supply External Power Adapter
Cooling Active Cooling System
Intended Use AI Development, LLM Inference, Fine-Tuning, Robotics, Edge AI