Hi Ryan,

From this information it sounds like you have 64 gradient directions for each b-value. The parameter ndir needs to be the number of gradient directions for each b-value, not the total amount of gradient directions. Consequently, your gradient vector text file should specify the gradient directions used for each bvalue. Often these will be the same for b1000 and b2000 and you can use one text file. If these  directions are not the same, you can supply two different text files (using the command line version). 

Here is some information from the manual: 
ndir:
Number of gradient directions. If a scalar value is specified, the number of gradient directions
for all b values is set to the scalar. Otherwise, a 1-by-(nbval-1) vector should be specified, with
each element of the vector corresponding to the number of gradient directions for a nonzero bvalue.
fn_gradients:
Text file containing the gradient vectors. Each row corresponds to a gradient vector. If a
different gradient set was used for each b-value, a 1-by-(nbval-1) cell array of file names should
be specified, with each cell specifying the gradient file name for the corresponding nonzero bvalue
idx_gradients
Indices of gradient directions to be used for DKI map estimation. Unacceptable diffusionweighted
images (e.g., those affected by motion- or patient table vibration-induced diffusion
signal loss) can be excluded here. There must be as many cells as there are nonzero b-values,
with each cell corresponding to a nonzero b-value.


Hope this helps! 
Emilie