diff --git a/py/torch_tensorrt/executorch/backend.py b/py/torch_tensorrt/executorch/backend.py
index b73d50eea2..2da1f73d03 100644
--- a/py/torch_tensorrt/executorch/backend.py
+++ b/py/torch_tensorrt/executorch/backend.py
@@ -282,16 +282,16 @@ def preprocess(
         _validate_engine_info(engine_info)
         serialized_engine = engine_info[ENGINE_IDX]
         if isinstance(serialized_engine, torch.Tensor):
-            # Single copy out of the underlying storage. The prior
-            # `.numpy().tobytes()` path allocated a fresh bytes buffer
-            # on top of the numpy view, which for a >2 GB engine
-            # roughly doubled peak memory at this step. `.cpu()` and
-            # `.contiguous()` are no-ops when already host-side and
-            # contiguous (the common case for the uint8 buffer this
-            # backend produces).
-            engine_info[ENGINE_IDX] = bytes(
-                serialized_engine.cpu().contiguous().untyped_storage()
-            )
+            # A single copy out of the tensor's own memory. `bytes(storage)` looks
+            # equivalent but iterates the storage element by element in Python,
+            # which costs about two seconds per megabyte and turns serializing a
+            # multi-gigabyte set of engines into hours. `memoryview` hands the
+            # buffer to the copy in one shot without the intermediate numpy view
+            # that would double peak memory for a large engine. `.cpu()` and
+            # `.contiguous()` are no-ops for the host-side uint8 buffer this
+            # backend normally produces.
+            engine_bytes = serialized_engine.cpu().contiguous().view(torch.uint8)
+            engine_info[ENGINE_IDX] = bytes(memoryview(engine_bytes.numpy()))
         elif not isinstance(serialized_engine, (bytes, bytearray)):
             engine_info[ENGINE_IDX] = bytes(serialized_engine)
         input_names = _reorder_input_names_for_executorch(