Infrared small target detection is a common task in infrared image processing, and computational resources are limited in application scenarios that require the use of infrared small target detection. Traditional IR small target detection methods face the problem of balancing detection rate and accuracy. In view of this, this paper designs a fast infrared small target detection method under resource-constrained conditions. This paper proposes a lightweight infrared small target detection method based on Yolo, which simultaneously takes into account the detection accuracy and detection rate of infrared targets. The experimental results show that the algorithm in this paper realizes the maximum 95FPS effective detection speed of infrared small targets on a 15W TPU, and at the same time achieves the maximum 91.9 effective detection accuracy, which effectively improves the detection efficiency of infrared small targets under resource-constrained conditions.