May be you can try following two servers for structure prediction.

http://robetta.bakerlab.org/

https://zhanglab.ccmb.med.umich.edu/I-TASSER/

These methods identify homology to domains/fragments/segments rather than the entire protein sequence in structural databases with the given protein sequence and constructs the model by stitching this information together.

Thanks for your answer.

I had already used I-TASSER server before I posted the question. The list score value of the models generated was -2.24. Since C-score of higher value indicates high confidence. With my little understanding I thought any value less than -1.5 is not a good quality model. Please, correct me if I am wrong. That is why I have not used the model

Thanks for your answer

You can refer to below attached paper full-text, which has all the methodology detials and link to webservers.

Thanks for your contribution.