Regression - pass vector & numeric feature as input

I need help in a regression scenario.I have 12 input features. 4 of which are coordinates(each is a vector) in XYZ plane (x1,y,z1), (x2,y2,z2),(x3,y3,z3), (x4,y4,z4) and remaining 8 are numeric features. I have 2 numeric target variables.

The coordinates refer to 4 object coordinates in space. These are not images, just coordinates in space.

How can I input the 4 coordinates into the neural network along with 8 other numeric features?

I know how to pass just the 8 numeric features while training. But, I am not sure how to pass the 4 coordinates that are vectors.

Thanks.