diff --git a/monai/transforms/intensity/array.py b/monai/transforms/intensity/array.py
index aefe5697b8..20000c52c4 100644
--- a/monai/transforms/intensity/array.py
+++ b/monai/transforms/intensity/array.py
@@ -907,8 +907,6 @@ def __call__(self, img: NdarrayOrTensor) -> NdarrayOrTensor:
             if self.divisor is not None and len(self.divisor) != len(img):
                 raise ValueError(f"img has {len(img)} channels, but divisor has {len(self.divisor)} components.")
 
-            img, *_ = convert_data_type(img, dtype=torch.float32)
-
             for i, d in enumerate(img):
                 img[i] = self._normalize(  # type: ignore
                     d,
diff --git a/tests/test_normalize_intensity.py b/tests/test_normalize_intensity.py
index 7efd0d83e5..72ebf579e1 100644
--- a/tests/test_normalize_intensity.py
+++ b/tests/test_normalize_intensity.py
@@ -108,27 +108,6 @@ def test_channel_wise(self, im_type):
         normalized = normalizer(input_data)
         assert_allclose(normalized, im_type(expected), type_test="tensor")
 
-    @parameterized.expand([[p] for p in TEST_NDARRAYS])
-    def test_channel_wise_int(self, im_type):
-        normalizer = NormalizeIntensity(nonzero=True, channel_wise=True)
-        input_data = im_type(torch.arange(1, 25).reshape(2, 3, 4))
-        expected = np.array(
-            [
-                [
-                    [-1.593255, -1.3035723, -1.0138896, -0.7242068],
-                    [-0.4345241, -0.1448414, 0.1448414, 0.4345241],
-                    [0.7242068, 1.0138896, 1.3035723, 1.593255],
-                ],
-                [
-                    [-1.593255, -1.3035723, -1.0138896, -0.7242068],
-                    [-0.4345241, -0.1448414, 0.1448414, 0.4345241],
-                    [0.7242068, 1.0138896, 1.3035723, 1.593255],
-                ],
-            ]
-        )
-        normalized = normalizer(input_data)
-        assert_allclose(normalized, im_type(expected), type_test="tensor", rtol=1e-7, atol=1e-7)  # tolerance
-
     @parameterized.expand([[p] for p in TEST_NDARRAYS])
     def test_value_errors(self, im_type):
         input_data = im_type(np.array([[0.0, 3.0, 0.0, 4.0], [0.0, 4.0, 0.0, 5.0]]))