`Range` parameter Variogram

Question

Why does the range parameter for this variogram differ so wildly?

I have an estimated and fitted Generalized Least Squares variogram but the values are vastly different.

#- extract the residuals into the point observations object
cfaq.sf$res.ts2.gls <- residuals(model.ts2.gls)
vr.gls <- variogram(res.ts2.gls ~ 1, loc=cfaq.sf, cutoff = 50000)
#- plot empirical variogram
plot(vr.gls, plot.numbers=T,
     main="Residuals from second-order GLS trend", cex=1,
     xlab = "separation [m]", ylab = "semivariance [m^2]")

plot(vr.gls, model=vr.gls.m.f, plot.numbers=T,
     xlab = "separation [m]", ylab = "semivariance [m^2]")

print(vr.gls.m.f)
  model      psill  range
1   Nug   14.08301      0
2   Exp 1848.77165 157050

intervals(model.ts2.gls)$corStruct[2]
[1] 2049.444

Surely the range parameter of the fitted variogram should be similar to the range parameter of the of the Generalized Least Squares fit?