This review provides an overview of AI models and tools in embedded IIoT applications. The integration of AI models into embedded platforms is crucial for enhancing operational efficiency, reducing latency, saving energy, improving data security, and increasing system resilience. The article discusses various AI models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Generative Adversarial Networks (GANs), along with Autoencoders, and their applications in IIoT contexts like fault prediction, process optimization, predictive maintenance, product quality control, cybersecurity, and machine control. It also examines software and hardware tools for integrating AI models into embedded platforms, including Vitis AI v3.5, TensorFlow Lite Micro v2.14, STM32Cube.AI v9.0, and others. The review highlights the importance of selecting appropriate AI models and tools based on the specific requirements of IIoT applications, considering factors such as computational efficiency, scalability, and adaptability. The article emphasizes the need for a systematic approach to evaluate and implement AI models in IIoT systems to achieve optimal performance and practical benefits in industrial settings.This review provides an overview of AI models and tools in embedded IIoT applications. The integration of AI models into embedded platforms is crucial for enhancing operational efficiency, reducing latency, saving energy, improving data security, and increasing system resilience. The article discusses various AI models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Generative Adversarial Networks (GANs), along with Autoencoders, and their applications in IIoT contexts like fault prediction, process optimization, predictive maintenance, product quality control, cybersecurity, and machine control. It also examines software and hardware tools for integrating AI models into embedded platforms, including Vitis AI v3.5, TensorFlow Lite Micro v2.14, STM32Cube.AI v9.0, and others. The review highlights the importance of selecting appropriate AI models and tools based on the specific requirements of IIoT applications, considering factors such as computational efficiency, scalability, and adaptability. The article emphasizes the need for a systematic approach to evaluate and implement AI models in IIoT systems to achieve optimal performance and practical benefits in industrial settings.