DX-H1 V-NPU

Power redefined — massive AI video at 40W,
making intelligence sustainable at scale

Overview

Integrated decoding, encoding, and transcoding turn the DX-H1 V-NPU into a complete foundation for real-time, large-scale monitoring. What once required rooms full of expensive, power-hungry servers can now be placed into the hands of any organization. The barrier to advanced AI falls away, and what remains is possibility, accessible, sustainable, and inevitable.

Featured Resources
HOST Server or PCx86 ARM Based Architecture
Features
Details
AI Performance
50 TOPS (=200 eTOPS / INT8) for real-time AI inference
SRAM
Genesis NPU: Internal SRAM, Codec Chip: 256 KB to 512 KB
CPU
Codec Chip: 4x Cortex-A76 (up to 2.4 GHz )
Codec Chip: 4x Cortex-A55 (up to 1.8 GHz)
Memory
Genesis NPU: Total = LPDDR5 8GB (4GB + 4GB)
Codec Chip: Total = LPDDR5 16GB (8GB + 8GB)
Storage
eMMC 32GB
Power Consumption
40W / 12V
PCIe
PCI Express Gen3 16X
Video Decoding
H.264 64CH (1080P @ 30FPS)
Video Encoding
H.264 32CH (1080P @ 30FPS)
Display
HDMI 2.0
Dimensions
167mm x 56mm x 19mm (TBD)
Host Hardware
x86, ARM Based Architecture

Key Benefits

Play Video

Revolutionary TCO82% lower hardware costs plus 85% electricity cost savings (1,000-channel system, 5-year basis). Transform expensive multi-server GPU setups into single, efficient edge cards accessible to any organization.

All-In-One ArchitectureDual hardware video codecs with dual NPUs handle complete video processing pipeline on a single card. This eliminates separate video decoders, minimizes CPU overhead on core systems, and ensures stable 24/7 operation without performance degradation.

Smart Monitoring SystemAdvanced edge processing analyzes video locally and transmits only critical events to VMS systems, drastically reducing bandwidth and storage costs. V-NPU's state-of-the-art AI models support enable natural language video search that transforms days of manual review into seconds of instant discovery.

Effortless ScalabilityCompact design without fan enables high-density deployments impossible with bulky GPUs. Deploy up to 4 cards per 2U server (256 channels) for maximum rack space efficiency and rapid scaling with existing infrastructure.

Related Products

Note: Performance metrics are based on the AI Model YOLOv5s_512 at 30 FPS.
Actual channel support may vary depending on the specific AI Model and FPS settings.
Product Models
Accelerator Configuration
AI Inference Performance
(Based YOLOv5, FHD, 30FPS)
Recommended Specifications
Certified Partners Products

Vision AI.
1U AI Workstation

Up to 4x
DX-H1 V-NPU
Up to 256 CH.
(Max. 7,680 FPS)
  • CPU: Intel® Xeon® W-2223 4C 1P
  • Memory: 32GB Memory or higher
  • Storage: 256GB SSD x 2
  • OS: Linux or Windows
  • DELL Precision Tower Workstation Series
  • HP Z Tower Workstation Series
  • Lenovo ThinkStation Tower Workstation Series

Vision AI.
1U AI Server

Up to 4x
DX-H1 V-NPU
Up to 256 CH.
(Max. 7,680 FPS)
  • CPU: Intel® or AMD 1.8GHz 8C 1P
  • Memory: 32GB Memory or higher
  • Storage: 256GB SSD x 2
  • OS: Linux or Windows
  • DELL PowerEdge R660 or R6615
  • HPE ProLiant DL320 Gen11 or DL325 Gen12
  • Lenovo ThinkSystem SR630 or SR635 V3
  • KAYTUS KR1280
  • Supermicro SYS-121H or 1125H

Vision AI.
1U AI Server

Up to 8x
DX-H1 V-NPU
Up to 512 CH.
(Max. 15,360 FPS)
  • CPU: Intel® or AMD 2.4GHz 12C 2P
  • Memory: 128GB Memory or higher
  • Storage: 256GB SSD x 2
  • OS: Linux or Windows
  • DELL PowerEdge R760 or R7625
  • HPE ProLiant DL380 or DL385 Gen11
  • Lenovo ThinkSystem SR650 or SR665 V3
  • KAYTUS KR2280
  • Supermicro SYS-221H or 621H

Use Cases

Security

Comprehensive perimeter monitoring and threat detection with advanced behavioral analysis, providing 24/7 surveillance while maintaining data privacy through local processing

Smart Buildings

Intelligent building management with integrated security and occupancy monitoring through local video analytics, ensuring tenant privacy while reducing infrastructure requirements

Smart Factory

On-site quality control and defect detection with superior thermal efficiency, operating reliably in harsh industrial environments without cooling systems

Smart Cities

Live traffic management and crowd monitoring with reduced bandwidth costs, processing thousands of camera feeds locally

Smart Safety Monitoring

Real-time workplace safety compliance and hazard detection with instant alert systems, enabling immediate response to safety violations and emergency situations

Content Delivery Network (Smart Search)

Transform video content libraries into searchable databases with natural language queries, reducing search time from hours to seconds

Logistics & Warehouses

Real-time inventory tracking and automated sorting with high-density camera deployments, enabling efficient operations and safety monitoring while reducing server infrastructure costs

Smart Transportation

Autonomous navigation and collision avoidance without network dependency, ensuring reliable operation regardless of connectivity conditions

Smart Retail

Real-time customer analytics and inventory management through local video processing, protecting customer privacy while optimizing operations

Trusted by Global Leaders

Global partners collaborate with DEEPX to bring on-device AI into real-world applications worldwide