Save your model or the weights of your model:
model.save(filename)
np.save(filename, model.get_weights())
For loading, in the first case:
from keras.models import load_model
model = load_model(filename)
In the second case:
#recreate the model then:
model.set_weights(np.load(filename))
Then:
results = model.predict(batch_of_data)