DX-M1
超紧凑 M.2 AI 加速模块
· 25 TOPS（INT8），高效支持大模型推理与计算机视觉任务
· PCIe Gen3 x4，向下兼容 Gen1/2，适配广泛平台
· 1W~5W 功耗，适配嵌入式与边缘设备场景
· 支持 Windows、Debian Linux、Yocto，x86/ARM 平台通用
· 兼容 Ultralytics、PyTorch、TensorFlow、ONNX 等开发框架
· 支持 Qwen、Gemma、Phi、MiniCPM 等主流开源大模型
Qwen
Gemini
Phi
MiniCPM
DX-M1 AI Module
DEEPX DX-M1 AI Module
Harness the complete capabilities of edge AI using the high-performance DEEPX DX-M1 acceleration module.
DEEPX DX-M1 AI Chip
Operating within an ultra-efficient 1–5W power envelope, the module delivers up to 200 GPU-class TOPS.
25 TOPS AI Engine
Designed for smooth integration into embedded and industrial systems, this small AI module provides up to 25 TOPS of AI performance.
AI-Optimized Architecture
The DX-M1 features a dedicated Neural Processing Unit (NPU) built specifically to improve deep learning performance.
Form Factor
M.2 2280(M Key), 22 x 80mm
AI Frameworks
Ultralytics, PyTorch, TensorFlow, ONNX, Keras
x86 and ARM
Supports x86 and ARM architectures
AI-powered solutions
Built in a standard form factor, the module can be easily deployed into existing platforms, enabling rapid development of AI-powered solutions
Developer-Ready Ecosystem
Provides extensive SDK resources
High-Performance Acceleration AI Module
Designed for seamless integration into embedded and industrial systems, this compact AI module delivers up to 25 TOPS of AI performance while maintaining exceptional energy efficiency at just ~3W typical power consumption.
应用场景
广泛应用于多个领域，如人脸识别、机器人、门禁控制、智能安防系统、智能网络摄像头以及更多领域。，为开发者提供一站式嵌入式与 AI 项目解决方案
智能摄像头
机器人技术
工业检测
智能交通
智能零售
自动化
硬件规格参数
| DX-M1M AI Module | ||
|---|---|---|
| Basic Specifications | AI Performance | 25 TOPS (INT8) Perfomance |
| Host Interface | PCIe Gen3 x2 (Supports Gen 1/2/3 & x1/x2) | |
| Memory | Integrated 2GB LPDDR4x (4266 MT/s) | |
| Power Consumption | 3W (Typical) | |
| Operating Temperature | -40 ~ 85°C (Industrial) | |
| Thermal Solution | Heatsink (Option) | |
| Form Factor | M.2 2242 (M+B Key), 22 x 42mm | |
| OS Support | Debian-based Linux, Windows 11/10, Yocto Project | |
| AI Frameworks | Ultralytics, PyTorch, TensorFlow, ONNX, Keras | |
| System Support | x86 and ARM-based Architectures | |
全流程定制化服务
KiwiPi 团队凭借 18 年产品设计、研发与制造领域的深厚经验，为客户提供从硬件设计、软件开发到整机方案的全流程定制服务，支持 ODM/OEM 合作模式，高效响应各类行业应用的个性化需求。