NVIDIA DGX Spark Personal AI Supercomputer 128GB RAM Unified Memory 4TB SSD – NVIDIA Blackwell Architecture – TechCure India

NVIDIA DGX Spark Personal AI Supercomputer | 128GB RAM Unified Memory, 4TB SSD | Grace Blackwell GB10

₹708,000

🚚 Free shipping across India on this product

EMI available at checkout (credit / debit card EMI via Razorpay)

In stock · dispatched in 1–2 working days
Delivery across India in 2–8 days · insured

Genuine productBrand warranty · terms
GST invoiceClaim input credit
7-day returnsOn PC components
Insured deliveryAll over India

Secure payments by Razorpay · UPI, cards, net banking, EMI

Track an order Google reviews ↗

The NVIDIA DGX Spark is a personal AI supercomputer designed to build and run AI models. It is built for users who need to prototype, fine-tune, and run inference on large models.

Full specifications ↓

Highlights

Build and run AI models using the NVIDIA Blackwell Architecture
Handle large datasets with 128 GB of coherent unified system memory
Secure your data with a 4 TB NVME.M2 SSD featuring self-encryption
Support for the FP4 data format for AI tasks
Built-in NVIDIA ConnectX network technology for high-speed connectivity
Includes a 200 Gbps ConnectX-7 NIC
Supports WiFi 7 and Bluetooth 5.4 with LE Audio-output
Runs on the specialized NVIDIA DGX OS

Specifications

Architecture	NVIDIA Grace Blackwell GPU
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	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	240 W
GB10 TDP*	140 W
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

Who should buy it

This is for AI developers who need to prototype and fine-tune large models locally. Users looking for a standard home computer should look at other products.

Compatibility

Two NVIDIA DGX Spark systems can be connected to work on even larger models such as Llama 3.1 405B.

Two NVIDIA DGX Spark systems can be connected to work on even larger models such as Llama 3.1 405B

What's in the box

NVIDIA DGX Spark

Frequently asked questions

What is the memory capacity?

It features 128 GB of LPDDR5x coherent unified system memory.

What storage does it have?

It includes a 4 TB NVME.M2 SSD with self-encryption.

Can it run very large models?

Two systems can be connected to work on models like Llama 3.1 405B.

Brand warranty: as per manufacturer from the manufacturer — TechCure India helps you with the claim.

Why buy from TechCure India

Genuine product with brand warranty
GST invoice on every order
Insured delivery across India
Free compatibility check before dispatch — or build a full PC with our PC Builder

Specifications

Brand	Nvidia
Category	Desktop
Architecture	NVIDIA Grace Blackwell GPU
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	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	240 W
GB10 TDP*	140 W
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
Condition	New, sealed box
Warranty	Manufacturer warranty · details
Invoice	GST tax invoice (input credit available)
Delivery	Insured shipping to every serviceable pin code in India