diff --git a/GPy/core/model.py b/GPy/core/model.py
index 8152dae1..89a2a3f0 100644
--- a/GPy/core/model.py
+++ b/GPy/core/model.py
@@ -118,12 +118,12 @@ class Model(Parameterized):
         """
         The objective function for the given algorithm.
 
-        This function is the true objective, which wants to be minimized. 
-        Note that all parameters are already set and in place, so you just need 
+        This function is the true objective, which wants to be minimized.
+        Note that all parameters are already set and in place, so you just need
         to return the objective function here.
 
         For probabilistic models this is the negative log_likelihood
-        (including the MAP prior), so we return it here. If your model is not 
+        (including the MAP prior), so we return it here. If your model is not
         probabilistic, just return your objective to minimize here!
         """
         return -float(self.log_likelihood()) - self.log_prior()
@@ -131,18 +131,18 @@ class Model(Parameterized):
     def objective_function_gradients(self):
         """
         The gradients for the objective function for the given algorithm.
-        The gradients are w.r.t. the *negative* objective function, as 
+        The gradients are w.r.t. the *negative* objective function, as
         this framework works with *negative* log-likelihoods as a default.
 
         You can find the gradient for the parameters in self.gradient at all times.
         This is the place, where gradients get stored for parameters.
 
-        This function is the true objective, which wants to be minimized. 
-        Note that all parameters are already set and in place, so you just need 
+        This function is the true objective, which wants to be minimized.
+        Note that all parameters are already set and in place, so you just need
         to return the gradient here.
 
         For probabilistic models this is the gradient of the negative log_likelihood
-        (including the MAP prior), so we return it here. If your model is not 
+        (including the MAP prior), so we return it here. If your model is not
         probabilistic, just return your *negative* gradient here!
         """
         return -(self._log_likelihood_gradients() + self._log_prior_gradients())
@@ -227,13 +227,15 @@ class Model(Parameterized):
 
         if optimizer is None:
             optimizer = self.preferred_optimizer
+        elif isinstance(optimizer, optimization.Optimizer):
+            opt = optimizer
+        else:
+            optimizer = optimization.get_optimizer(optimizer)
+            opt = optimizer(start, model=self, **kwargs)
 
         if start == None:
             start = self.optimizer_array
 
-        optimizer = optimization.get_optimizer(optimizer)
-        opt = optimizer(start, model=self, **kwargs)
-
         opt.run(f_fp=self._objective_grads, f=self._objective, fp=self._grads)
 
         self.optimization_runs.append(opt)