The Internet of Things (IoT) is now present in every domain from applications in smart homes, Smart Cities, Industrial Internet of Things (IIoT), such as e-Health, and beyond. The wide use of Internet of Things is making its security a real concern. Techniques based on artificial intelligence (AI) and its subsets machine learning (ML) and deep learning (DL) are commonly used to develop a secure Intrusion Detection System (IDS) for IoT. Researchers and industrialists are commonly using commercial Internet of Things devices, broadly available on the market. In this paper, we present an analysis of the possibility to deploy a Deep Learning-Based Host-Intrusion Detection System (DL-HIDS) on some specific commercial IoT devices. We performed multiple optimizations regarding the types of our used devices to meet their limited hardware specifications. In our conducted analysis, we consider such criteria, as memory consumption and inference timing (attacks prediction timing), to conclude which model fits better to our proposed lightweight DL-HIDS for each studied device, and to anticipate about which IDS we must generate and expectedly deploy based on the characteristics of the devices we possess. The paper also discusses the proposed methodology for such deployment in a real IoT environment. The obtained results about the implementation of our DL-HIDS on different considered devices (up to 99.74% in accuracy and an inference of not more of 1µs for attacks prediction) are promising and prove that we can manage to install a suited IDS for each device, but it should be minutiously supported by a central IDS in fog or cloud layers.