diff --git a/sagemaker-serve/src/sagemaker/serve/mode/local_container_mode.py b/sagemaker-serve/src/sagemaker/serve/mode/local_container_mode.py
index f71f227ea6..259119d0f2 100644
--- a/sagemaker-serve/src/sagemaker/serve/mode/local_container_mode.py
+++ b/sagemaker-serve/src/sagemaker/serve/mode/local_container_mode.py
@@ -201,7 +201,6 @@ def create_server(
         time.sleep(10)
 
         log_generator = self.container.logs(follow=True, stream=True)
-        container_timeout_seconds = 1200
         time_limit = datetime.now() + timedelta(seconds=container_timeout_seconds)
         healthy = False
         while True:
diff --git a/sagemaker-serve/tests/unit/mode/test_local_container_mode_timeout.py b/sagemaker-serve/tests/unit/mode/test_local_container_mode_timeout.py
new file mode 100644
index 0000000000..87243a81b0
--- /dev/null
+++ b/sagemaker-serve/tests/unit/mode/test_local_container_mode_timeout.py
@@ -0,0 +1,68 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You
+# may not use this file except in compliance with the License. A copy of
+# the License is located at
+#
+#     http://aws.amazon.com/apache2.0/
+#
+# or in the "license" file accompanying this file. This file is
+# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
+# ANY KIND, either express or implied. See the License for the specific
+# language governing permissions and limitations under the License.
+"""LocalContainerMode.create_server must honor the requested container timeout."""
+
+from __future__ import absolute_import
+
+from datetime import datetime, timedelta
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+import sagemaker.serve.mode.local_container_mode as local_container_mode
+from sagemaker.serve.mode.local_container_mode import LocalContainerMode
+from sagemaker.serve.utils.exceptions import LocalDeepPingException
+from sagemaker.serve.utils.types import ModelServer
+
+
+@pytest.mark.parametrize("timeout_seconds", [60, 1800])
+def test_create_server_gives_up_after_requested_timeout(timeout_seconds):
+    clock = {"now": datetime(2026, 1, 1)}
+
+    class FakeDatetime:
+        @staticmethod
+        def now():
+            return clock["now"]
+
+    def fake_sleep(seconds):
+        clock["now"] += timedelta(seconds=seconds)
+
+    mode = LocalContainerMode(
+        ModelServer.TORCHSERVE, None, None, MagicMock(), model_path="/tmp/model"
+    )
+    container = MagicMock()
+
+    with (
+        patch.object(mode, "_pull_image"),
+        patch.object(
+            mode,
+            "_start_torch_serve",
+            side_effect=lambda **_: setattr(mode, "container", container),
+        ),
+        patch.object(local_container_mode, "datetime", FakeDatetime),
+        patch.object(local_container_mode.time, "sleep", side_effect=fake_sleep),
+        patch.object(local_container_mode, "pull_logs"),
+    ):
+        start = clock["now"]
+        with pytest.raises(LocalDeepPingException):
+            mode.create_server(
+                image="image",
+                container_timeout_seconds=timeout_seconds,
+                secret_key="",
+                container_config={},
+                ping_fn=lambda: (False, None),
+            )
+
+    waited = (clock["now"] - start).total_seconds()
+    # 10s initial grace period plus at most one 10s polling interval past the deadline.
+    assert timeout_seconds <= waited <= timeout_seconds + 30