diff --git a/backends/cortex_m/ops/TARGETS b/backends/cortex_m/ops/TARGETS
index 12044266ca1..18b387c8ad2 100644
--- a/backends/cortex_m/ops/TARGETS
+++ b/backends/cortex_m/ops/TARGETS
@@ -17,6 +17,7 @@ runtime.python_library(
     deps = [
         "fbcode//caffe2:torch",
         "//executorch/backends/cortex_m/passes:passes_utils",
+        "//executorch/backends/cortex_m/quantizer:quantization_configs",
     ],
 )
 
diff --git a/backends/cortex_m/quantizer/TARGETS b/backends/cortex_m/quantizer/TARGETS
new file mode 100644
index 00000000000..0af105efef0
--- /dev/null
+++ b/backends/cortex_m/quantizer/TARGETS
@@ -0,0 +1,36 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+load("@fbcode_macros//build_defs:python_library.bzl", "python_library")
+
+oncall("executorch")
+
+python_library(
+    name = "quantizer",
+    srcs = [
+        "__init__.py",
+        "operator_configs.py",
+        "quantization_configs.py",
+        "quantizer.py",
+    ],
+    deps = [
+        "//caffe2:torch",
+        "//executorch/backends/arm/quantizer:quantization_config",
+        "//pytorch/ao:torchao",
+    ],
+)
+
+python_library(
+    name = "quantization_configs",
+    srcs = [
+        "quantization_configs.py",
+    ],
+    deps = [
+        "//caffe2:torch",
+        "//executorch/backends/arm/quantizer:quantization_config",
+        "//pytorch/ao:torchao",
+    ],
+)
diff --git a/backends/cortex_m/quantizer/__init__.py b/backends/cortex_m/quantizer/__init__.py
new file mode 100644
index 00000000000..39a3de431ff
--- /dev/null
+++ b/backends/cortex_m/quantizer/__init__.py
@@ -0,0 +1,19 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+from .quantization_configs import (  # noqa
+    CMSIS_SOFTMAX_SCALE,
+    CMSIS_SOFTMAX_ZERO_POINT,
+    INT8_ACTIVATION_PER_CHANNEL_QSPEC,
+    INT8_ACTIVATION_PER_TENSOR_QSPEC,
+    INT8_PER_CHANNEL_CONFIG,
+    INT8_PER_TENSOR_CONFIG,
+    INT8_WEIGHT_PER_CHANNEL_QSPEC,
+    INT8_WEIGHT_PER_TENSOR_QSPEC,
+    SOFTMAX_OUTPUT_FIXED_QSPEC,
+    SOFTMAX_PER_TENSOR_CONFIG,
+)
+from .quantizer import CortexMQuantizer, SharedQspecQuantizer  # noqa