Fire incidents in urban and forested areas pose serious threats, underscoring the need for more effective detection technologies. In order to overcome these difficulties, we present CCi-YOLOv8n, an enhanced YOLOv8 model with targeted improvements to detect small fires and smoke. The model integrates the CARAFE upsampling operator and a context-guided module to reduce information loss during upsampling and downsampling, thereby retaining richer feature representations. Furthermore, an inverted residual mobile block enhanced C2f module captures small targets and fine smoke patterns, a critical improvement over the original model’s detection capacity. For validation, we introduce Web-Fire, a dataset curated for fire and smoke detection in a range of real-world situations. The experimental results indicate that CCi-YOLOv8n outperforms YOLOv8n in detection precision, confirming its effectiveness for robust fire detection tasks.