is it possible to run only FM model

[Sandy4321]

what performance are for Fm model?
do you support spars data format
can you run this data example
http://srome.github.io/Leveraging-Factorization-Machines-for-Sparse-Data-and-Supervised-Visualization/

with
X_train.shape
#(7580, 1048576)
where number if features is 1048576?