diff --git a/src/bindings/python/tests/test_runtime/test_core.py b/src/bindings/python/tests/test_runtime/test_core.py
index a864f73228106b..33540294117909 100644
--- a/src/bindings/python/tests/test_runtime/test_core.py
+++ b/src/bindings/python/tests/test_runtime/test_core.py
@@ -65,7 +65,8 @@ def test_core_class(device):
 
     input_tensor = Tensor(input_data)
     results = request.infer({"data": input_tensor})
-    assert np.allclose(results[list(results)[0]], expected_output)
+    # convert node may be introduced by API 2.0, which brings some deviation
+    assert np.allclose(results[list(results)[0]], expected_output, 1e-4, 1e-4)
 
 
 # request - https://docs.pytest.org/en/7.1.x/reference/reference.html#request
diff --git a/src/bindings/python/tests/test_runtime/test_infer_request.py b/src/bindings/python/tests/test_runtime/test_infer_request.py
index 85e4296f691081..8b04e915a8923d 100644
--- a/src/bindings/python/tests/test_runtime/test_infer_request.py
+++ b/src/bindings/python/tests/test_runtime/test_infer_request.py
@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 # Copyright (C) 2018-2023 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
+import platform
 
 from collections.abc import Iterable
 from copy import deepcopy
@@ -97,7 +98,12 @@ def abs_model_with_data(device, ov_type, numpy_dtype):
 
 def test_get_profiling_info(device):
     core = Core()
-    param = ops.parameter([1, 3, 32, 32], np.float32, name="data")
+    if platform.system() == "Darwin" and platform.machine() == "arm64":
+        # arm64 prefers fp16, and fp32 input will trigger a convert node
+        # to be added, so assert 'Softmax' will failed.
+        param = ops.parameter([1, 3, 32, 32], np.float16, name="data")
+    else:
+        param = ops.parameter([1, 3, 32, 32], np.float32, name="data")
     softmax = ops.softmax(param, 1, name="fc_out")
     model = Model([softmax], [param], "test_model")
 
diff --git a/src/plugins/intel_cpu/src/transformations/transformation_pipeline.cpp b/src/plugins/intel_cpu/src/transformations/transformation_pipeline.cpp
index 95bbe6cb1c7308..e9558163fe8b28 100644
--- a/src/plugins/intel_cpu/src/transformations/transformation_pipeline.cpp
+++ b/src/plugins/intel_cpu/src/transformations/transformation_pipeline.cpp
@@ -294,9 +294,12 @@ void Transformations::PreLpt(const std::vector<ov::element::Type>& defaultPrecis
         };
         type_to_fuse_map empty_fuse_map = {};
         const bool keep_precision_sensitive_in_fp32 = true;
-        CPU_REGISTER_PASS_COMMON(manager, ov::pass::ConvertPrecision, fp_convert_precision_map,
-                                                                      empty_fuse_map,
-                                                                      keep_precision_sensitive_in_fp32);
+        CPU_REGISTER_PASS_COMMON(manager,
+                                 ov::pass::ConvertPrecision,
+                                 fp_convert_precision_map,
+                                 empty_fuse_map,
+                                 keep_precision_sensitive_in_fp32,
+                                 false);
     }
 #endif
     CPU_REGISTER_PASS_COMMON(manager, ov::pass::KeepConstAndDecompression);