<p>Time series are widely present in various fields such as financial investment, energy consumption, electricity usage, and traffic flow. By analyzing time series, we can predict future trends and patterns, which helps in making strategic decisions, optimizing resource allocation, and improving overall efficiency. Recently, most methods prioritize prediction accuracy, often overlooking memory and computational costs, which limit applicability in scenarios requiring rapid response times or high computational resources. Even when focusing solely on prediction accuracy, these methods often overlook important considerations, such as the interactions between time and frequency features, among channels, and within patches. To address these issues, we designed a lightweight time series forecasting model called TFP-Mixer, which integrates both time domain and frequency domain information. In the time domain, TFP-Mixer captures the dynamic changes and dependencies of time series through Time/Frequency interaction, Channel interaction, and Patch interaction. By using Discrete Fourier transform (DFT) to convert time series into frequency domain data, the model extracts and interacts with frequency domain features, enhancing its ability to capture frequency domain characteristics. Extensive experiments on nine real-world time series datasets show that TFP-Mixer achieves a 6.17% and 7.15% improvement over state-of-the-art (SOTA) methods. The code is available at <a href="https://github.com/SDUYanDong/TFP-Mixer">https://github.com/SDUYanDong/TFP-Mixer</a></p>