Text summarization is the procedure of transferring the lengthy documents into small without disturbing the original meaning and important information of the document. Summarization reduces the size of the content so that the time can be saved tremendously. The LLMs used to yield better results for enhancing text summarization techniques. The advancement in LLMs have given space for text summarization and also provide various capabilities for fine-tuning to improve the performance of the task. The aim of this work is to explore the role of various LLMs in text summarization and the refinement of the experiment by changing the hyperparameters then the results are evaluated to measure the summarization process. This work explores the different LLM models such as T5, MPT-1.5b-instruct, OpenAI ChatGPT text-davinci-003, falcon-7b-instruct and the results are like human generated text which is considered as a remarkable achievement in the domain of NLP. The evaluation metrics are BLEU, ROUGH, and Bert scores calculated and the quality of the summarization results are compared to give a right direction to the researchers.