diff --git a/examples/efficientnet.py b/examples/efficientnet.py
index 791ef30b07..1f73cfdf32 100644
--- a/examples/efficientnet.py
+++ b/examples/efficientnet.py
@@ -10,7 +10,7 @@ import time
 import numpy as np
 np.set_printoptions(suppress=True)
 from tinygrad.tensor import Tensor
-from tinygrad.utils import fetch, get_parameters
+from extra.utils import fetch, get_parameters
 from extra.efficientnet import EfficientNet
 
 def infer(model, img):
diff --git a/examples/serious_mnist.py b/examples/serious_mnist.py
index c58500f7a5..882dba11bd 100644
--- a/examples/serious_mnist.py
+++ b/examples/serious_mnist.py
@@ -7,8 +7,8 @@ sys.path.append(os.path.join(os.getcwd(), 'test'))
 
 from tinygrad.tensor import Tensor
 from tinygrad.nn import BatchNorm2D
-from tinygrad.utils import get_parameters
 import tinygrad.optim as optim
+from extra.utils import get_parameters
 
 # TODO: abstract this generic trainer out of the test
 from test_mnist import train as train_on_mnist
diff --git a/examples/train_efficientnet.py b/examples/train_efficientnet.py
index c195e78344..e806f5ef3d 100644
--- a/examples/train_efficientnet.py
+++ b/examples/train_efficientnet.py
@@ -3,7 +3,7 @@ import time
 import numpy as np
 from extra.efficientnet import EfficientNet
 from tinygrad.tensor import Tensor
-from tinygrad.utils import get_parameters, fetch
+from extra.utils import get_parameters, fetch
 from tqdm import trange
 import tinygrad.optim as optim
 import io
diff --git a/extra/efficientnet.py b/extra/efficientnet.py
index 8350c80ca0..cd32acfab6 100644
--- a/extra/efficientnet.py
+++ b/extra/efficientnet.py
@@ -1,8 +1,8 @@
 import math
 import numpy as np
 from tinygrad.tensor import Tensor
-from tinygrad.utils import fetch
 from tinygrad.nn import BatchNorm2D
+from extra.utils import fetch
 
 USE_TORCH = False
 
diff --git a/test/test_mnist.py b/test/test_mnist.py
index 1326f1ac68..35e4cd4549 100644
--- a/test/test_mnist.py
+++ b/test/test_mnist.py
@@ -3,8 +3,8 @@ import os
 import unittest
 import numpy as np
 from tinygrad.tensor import Tensor, GPU
-from tinygrad.utils import fetch, get_parameters
 import tinygrad.optim as optim
+from extra.utils import fetch, get_parameters
 from tqdm import trange
 
 # mnist loader
diff --git a/test/test_optim.py b/test/test_optim.py
index 4038e001ab..0dc1976ce3 100644
--- a/test/test_optim.py
+++ b/test/test_optim.py
@@ -3,7 +3,7 @@ import torch
 import unittest
 from tinygrad.tensor import Tensor, GPU
 from tinygrad.optim import Adam, SGD, RMSprop
-from tinygrad.utils import get_parameters 
+from extra.utils import get_parameters
 
 x_init = np.random.randn(1,3).astype(np.float32)
 W_init = np.random.randn(3,3).astype(np.float32)
diff --git a/tinygrad/__init__.py b/tinygrad/__init__.py
index 242f072193..0deab3e967 100644
--- a/tinygrad/__init__.py
+++ b/tinygrad/__init__.py
@@ -1,4 +1,3 @@
 import tinygrad.optim
 import tinygrad.tensor
-import tinygrad.utils
 import tinygrad.nn