DEEPX AI Modules Line-up
Powering the Future of Edge AI

DX-M Series
DX-M1 M.2 LPDDR5x2
Type: AI Accelerator
AI Perf: 25 TOPS / 3~5 W

DX-M Series
DX-M1M M.2 2242
(Coming Soon)
Type: AI Accelerator
AI Perf: TBU

DX-H Series
DX-H1 PCIe Card Quattro
Type: AI Accelerator
AI Perf: 100 TOPS / 20 W

DX-H Series
DX-H1 PCIe Card Dual V-NPU (Coming Soon)
Type: AI Accelerator (Decoding 64 CH.)
AI Perf: 50 TOPS

DX-V Series
DX-V3 IPCam DX-Cam
(Coming Soon)
Type: AI Vision SoC
AI Perf: 13 TOPS

DX-M1 M.2 LPDDR5x2
DX-M Series
AI Performance
25 TOPS / 3~5 W
Form Factor
M.2 M Key (22 x 80 mm)
Interface
PCle Gen.3 x4
Memory
4GB LPDDR5, QSPI 1Gbit NAND Flash
Host Hardware
x86, ARM Based Architecture
AI Performance
AI Model | Input Resolution | Accuracy (mAP)
FP32 GPU | Accuracy (mAP) *IQ8 DX-M1 | FPS DX-M1 | NPU Power (W) DX-M1 | FPS/W DX-M1 |
---|---|---|---|---|---|---|
YOLOv5m6 | 640×640 | 45.08 | 45.07 | 40.42 | 2.20 | 18.37 |
YOLOv7-e6 | 640×640 | 55.58 | 55.45 | 19.49 | 2.50 | 7.81 |
YOLOv8x | 640×640 | 53.63 | 53.12 | 49.03 | 3.17 | 15.48 |
YOLOv8l | 640×640 | 52.57 | 52.01 | 91.13 | 3.60 | 25.32 |
YOLOv8m | 640×640 | 50.11 | 49.56 | 133.60 | 2.76 | 48.32 |
YOLOv9c | 640×640 | 52.86 | 52.36 | 47.89 | 2.83 | 16.95 |
- *This is the test result of Pro compilation among Pro and Master of DEEPX compiler.
- *IQ8: High-accuracy AI processing using efficient INT8 operations.

DX-M1M M.2 2242
DX-M Series
AI Performance
TBU
Form Factor
M.2 B+M Key (22 x 42 mm)
Interface
PCle Gen.3 x 2
Memory
4GB LPDDR4x, QSPI 1Gbit NAND Flash
Host Hardware
x86, ARM Based Architecture

DX-H1 PCIe Card Quattro
DX-H Series
AI Performance
100 TOPS / 20 W
Form Factor
PCIe Card (167mm x 66.4mm)
Interface
PCIe Gen.3 (4 x 4 x 4 x 4 Bifurcation)
Memory
16GB LPDDR5, QSPI 1Gbit NAND Flash
Host Hardware
x86, ARM Based Architecture

DX-H1 PCIe Card Dual V-NPU
DX-H Series
AI Performance
50 TOPS
Decoding
64 CH.
Form Factor
Low Profile (168 x 70mm)
Interface
PCIe Gen.3 (2 x 2 x 2 x 2 Bifurcation)
Memory
TBD
Host Hardware
x86, ARM Based Architecture

DX-V3 IPCam DX-Cam
DX-V Series
AI Performance
13 TOPS
Form Factor
TBU
Interface
TBU
Memory
2GB LPDDR5, eMMC 32GB, QSPI 1Gbit NAND Flash
Camera Sensor
MIPI CSI-2
Frequently Asked Questions
What is an AI Accelerator?
An AI Accelerator, also known as an NPU (Neural Processing Unit) or AI Chip, is an integrated chip specifically designed to run artificial intelligence software by executing machine learning models.
What is the biggest difference between an AI Accelerator and an AI Vision SoC?
An AI Accelerator is a general AI processor that enhances AI/ML tasks across various domains. In contrast, an AI Vision SoC is specialized for computer vision, integrating both AI processing and image-related hardware.
How can I test the products?
You can purchase the Evaluation Kit from our website (Buy Now) and proceed with testing.