Within the past few a long time, the broad utilize of profound learning models has driven to huge enhancements in numerous regions. Be that as it may, their tall handling needs are still an issue, particularly in places with restricted assets. This think about tries to unravel these problems by proposing a better approach to utilize trimming and quantization together to form profound learning models utilize the slightest sum of energy conceivable. By carefully evacuating unnecessary links or parameters from the organize, pruning brings down the sum of work that should be done on the computer, and quantization reduces the model’s parameters to less exact representations, which assist brings down the sum of memory and work that should be done on the computer. By integrating these strategies, it conserves energy without compromising performance. In this paper, the test results demonstrate that the proposed strategy performs well with various deep learning models and datasets. Moreover this paper appears the qualities and shortcoming of the tradeoffs between show exactness and energy reserve funds, appearing how they may be utilized within the genuine world. Generally, this consider includes to the continuous work of making profound learning models that utilize less energy, which makes a difference with natural issues and makes it conceivable to utilize AI frameworks in places with restricted assets.