diff --git a/tests/tt_eager/python_api_testing/unit_testing/misc/test_transpose.py b/tests/tt_eager/python_api_testing/unit_testing/misc/test_transpose.py
index 59b00643792..cc7f5effc75 100644
--- a/tests/tt_eager/python_api_testing/unit_testing/misc/test_transpose.py
+++ b/tests/tt_eager/python_api_testing/unit_testing/misc/test_transpose.py
@@ -1085,7 +1085,13 @@ def test_transpose_hw_sharded_tiled_n_cores(device, n, c, h, w):
 def test_transpose_hw_rm(shape, device):
     torch_input = torch.randn(shape, dtype=torch.bfloat16)
     torch_output = torch_input.transpose(2, 3)
-    tt_input = ttnn.from_torch(torch_input, dtype=ttnn.DataType.BFLOAT16, layout=ttnn.ROW_MAJOR_LAYOUT, device=device)
+    tt_input = ttnn.from_torch(
+        torch_input,
+        dtype=ttnn.DataType.BFLOAT16,
+        layout=ttnn.ROW_MAJOR_LAYOUT,
+        device=device,
+        memory_config=ttnn.L1_MEMORY_CONFIG,
+    )
     tt_output = ttnn.transpose(tt_input, 2, 3)
     tt_output = ttnn.to_torch(tt_output)
     assert_with_pcc(torch_output, tt_output, 0.9999)
diff --git a/ttnn/cpp/ttnn/operations/core/to_memory_config/to_memory_config_op.hpp b/ttnn/cpp/ttnn/operations/core/to_memory_config/to_memory_config_op.hpp
index 6c4d1f2be94..be1ba18574d 100644
--- a/ttnn/cpp/ttnn/operations/core/to_memory_config/to_memory_config_op.hpp
+++ b/ttnn/cpp/ttnn/operations/core/to_memory_config/to_memory_config_op.hpp
@@ -28,7 +28,6 @@ struct ToMemoryConfig {
         std::optional<ttnn::DataType> dtype = std::nullopt) {
         // Temporary until we see why buffer data not being populated
         const auto original_shape = tensor.get_shape();
-
         const auto original_memory_config = ttnn::get_memory_config(tensor);
         if (original_memory_config.has_value() && original_memory_config.value() == memory_config) {
             return tensor;
diff --git a/ttnn/cpp/ttnn/operations/data_movement/fold/fold.cpp b/ttnn/cpp/ttnn/operations/data_movement/fold/fold.cpp
index a4487842fd6..754ea6e24b1 100644
--- a/ttnn/cpp/ttnn/operations/data_movement/fold/fold.cpp
+++ b/ttnn/cpp/ttnn/operations/data_movement/fold/fold.cpp
@@ -12,7 +12,6 @@
 #include "ttnn/cpp/ttnn/operations/data_movement/reshape_on_device/reshape.hpp"
 #include "ttnn/cpp/ttnn/operations/data_movement/pad/pad.hpp"
 #include "tt_metal/common/constants.hpp"
-#include "ttnn/cpp/ttnn/operations/data_movement/transpose/device/transpose_op.hpp"
 
 #include "fold.hpp"
 
@@ -63,8 +62,7 @@ std::vector<Tensor> fold_with_transpose_(
     tt::log_debug("pad_output: {}", pad_output.shape());
 
     // transpose
-    auto transpose_hw_output = operation::run(Transpose{TransposeOpDim::WH, L1_mem_config, 0.0f}, {pad_output})
-                                   .at(0);  // ttnn::transpose(pad_output, 2, 3, L1_mem_config);
+    auto transpose_hw_output = ttnn::transpose(pad_output, 2, 3, L1_mem_config);
 
     tt::log_debug("transpose_hw_output: {}", transpose_hw_output.shape());
 
@@ -82,8 +80,7 @@ std::vector<Tensor> fold_with_transpose_(
     tt::log_debug("reshape_hc_output: {}", reshape_hc_output.shape());
 
     // transpose
-    auto transpose_hw_output2 =
-        operation::run(Transpose{TransposeOpDim::WH, L1_mem_config, 0.0f}, {reshape_hc_output}).at(0);
+    auto transpose_hw_output2 = ttnn::transpose(reshape_hc_output, 2, 3, L1_mem_config);
 
     tt::log_debug("transpose_hw_output2: {}", transpose_hw_output2.shape());
 
diff --git a/ttnn/cpp/ttnn/operations/data_movement/permute/device/permute_device_operation.cpp b/ttnn/cpp/ttnn/operations/data_movement/permute/device/permute_device_operation.cpp
index 8bc4bece3b0..b3a6db38548 100644
--- a/ttnn/cpp/ttnn/operations/data_movement/permute/device/permute_device_operation.cpp
+++ b/ttnn/cpp/ttnn/operations/data_movement/permute/device/permute_device_operation.cpp
@@ -51,7 +51,12 @@ PermuteDeviceOperation::tensor_return_value_t PermuteDeviceOperation::create_out
     }
     auto output_shape = compute_output_shapes(operation_attributes, tensor_args);
     const auto& input_tensor = tensor_args.input_tensor;
-    return create_device_tensor(output_shape, input_tensor.dtype(), input_tensor.layout(), input_tensor.device());
+    return create_device_tensor(
+        output_shape,
+        input_tensor.dtype(),
+        input_tensor.layout(),
+        input_tensor.device(),
+        operation_attributes.output_mem_config);
 }
 
 std::tuple<PermuteDeviceOperation::operation_attributes_t, PermuteDeviceOperation::tensor_args_t>