AMD RYZEN 7 9800X3D 8-Core, 16-Thread Desktop Processor2,299.00
NVIDIA DGX Spark
NVIDIA DGX Spark AI Supercomputer – GB10 Grace Blackwell, 128GB LPDDR5X, 4TB NVMe
- In Stock
- Brand: nvidia
30,899.00
VAT INCLUSIVE
Customers also bought
AMD RYZEN 7 9800X3D 8-Core, 16-Thread Desktop Processor
Asus ROG Astral GeForce RTX™ 5080 Dhahab CORE OC Edition9,999.00 7,999.00
Samsung 870 EVO 1TB SATA 2.5-inch SSD | 560MB/s Read | 530MB/s Write799.00
ASUS ROG Swift PG65UQ 65-inch 4K UHD 144Hz HDR Gaming Monitor with NVIDIA G-SYNC Ultimate14,999.00 9,499.00
ASUS ROG Swift OLED PG32UCDM3 Gen 3 32” 4K 240Hz Tandem QD-OLED Gaming Monitor – 0.03ms, BlackShield, G-SYNC, DisplayPort 2.1a6,399.00 6,149.00
ASUS TUF Gaming GT502 Horizon TG ARGB White – Mid Tower Gaming Case729.00
AORUS GeForce RTX 5090 MASTER 32GB GDDR7 PCIe 5.0 Graphics Card with WINDFORCE and LCD29,999.00
Gaming PC Intel Core i5-14400F RTX 5060 Ti 8GB, 16GB DDR5 1TB NVMe SSD5,799.00
NVIDIA • DESKTOP AI SUPERCOMPUTER
NVIDIA DGX SPARK AI power on your desk.
NVIDIA DGX Spark belongs to a new class of computers designed to build and run AI, enabling developers to prototype, fine-tune, and inference large AI models locally, then move workflows to the data center or cloud.
1 PFLOPTheoretical FP4 Tensor performance using sparsity
128GBLPDDR5x Unified System Memory
273 GB/sMemory Bandwidth
4TBNVMe M.2 Self-Encrypting Storage
NVIDIA GB10 SUPERCHIP
Grace Blackwell in a desktop system
1 PFLOP
Experience up to 1 petaFLOP of AI performance at FP4 precision with NVIDIA Grace Blackwell architecture, a Blackwell architecture GPU, and a 20-core Arm CPU.
GPU — Blackwell Architecture
CPU — 20 Core Arm: 10 Cortex-X925 + 10 Cortex-A725
Tensor Cores — 5th Generation
RT Cores — 4th Generation
COHERENT UNIFIED MEMORY
Unified memory for large AI workloads
128GB
128GB of LPDDR5x unified system memory with a 256-bit memory interface and 273 GB/s of memory bandwidth. The official specifications state that DGX Spark can run AI development and testing workloads with models up to 200 billion parameters.
128GB LPDDR5x Unified System Memory
256-bit Memory Interface
273 GB/s Memory Bandwidth
AI Models up to 200B Parameters
NVIDIA CONNECT-X NETWORKING
Connect two systems. Work with larger models.
405B
High-performance NVIDIA Connect-X networking enables two NVIDIA DGX Spark systems to be connected together to work with AI models up to 405 billion parameters.
ConnectX-7 Smart NIC
10 GbE — 1× RJ-45
High-performance networking for dual-system workflows
COMPACT DESKTOP FORM
Advanced AI in a compact desktop form
1.2 KG
A compact 150 × 150 × 50.5 mm desktop system weighing 1.2 kg, with 4TB NVMe M.2 self-encrypting storage and NVIDIA DGX OS.
150 × 150 × 50.5 mm
System Weight — 1.2 kg
4TB NVMe M.2 with Self-Encryption
DGX OS
OFFICIAL PRODUCT VIEWS
See DGX Spark from multiple angles
Official product images are integrated directly into the presentation to clearly show the design and system connections.
SYSTEM CONNECTIONS
Ports and connectivity
The following connectivity specifications are taken from the official product specifications.
4× USB Type-CFour USB Type-C ports; one provides power.
HDMI 2.1aDirect display connection; official specifications list support up to 8K at 120Hz with HDR.
10 GbE RJ-4510 Gigabit Ethernet via RJ-45.
Wi-Fi 7 + BT 5.3Modern wireless connectivity per the published specifications.
FULL OFFICIAL SPECIFICATIONS
Technical specifications
All values below are taken from the official specifications for product NVDGXSPARK-PB.
PART NUMBERNVDGXSPARK-PB
ARCHITECTURENVIDIA Grace Blackwell
GPUBlackwell Architecture
CPU20 Core Arm — 10 Cortex-X925 + 10 Cortex-A725
CUDA CORESBlackwell Generation
TENSOR CORES5th Generation
RT CORES4th Generation
TENSOR PERFORMANCE1 PFLOP¹
SYSTEM MEMORY128GB LPDDR5x Unified System Memory
MEMORY INTERFACE256-bit
MEMORY BANDWIDTH273 GB/s
OSDGX OS
STORAGE4 TB NVMe M.2 with Self-Encryption
USB4× USB Type-C
ETHERNET10 GbE — 1× RJ-45
NICConnectX-7 Smart NIC
WI-FIWi-Fi 7
BLUETOOTHBT 5.3
AUDIOHDMI Multichannel Audio Output
DISPLAY1× HDMI 2.1a
NVENC | NVDEC1× | 1×
DIMENSIONS150 × 150 × 50.5 mm
WEIGHT1.2 kg
¹ Theoretical FP4 performance using the sparsity feature. Specifications are preliminary and subject to change.
