diff --git a/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py b/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py
index 3e9f9a6544..eb7bbec997 100644
--- a/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py
+++ b/onnxruntime/python/tools/quantization/matmul_4bits_quantizer.py
@@ -349,6 +349,10 @@ class MatMul4BitsQuantizer:
             self.int4_quant_algo()
 
 
+def ort_convert_str_to_bool(value):
+    return value.lower() in ("true", "1")
+
+
 def parse_args():
     parser = argparse.ArgumentParser(
         description="""Blockwise int4 quantization for MatMul 2D weight matrices.
@@ -366,7 +370,10 @@ set of 4b integers with a scaling factor and an optional offset.
         "--symmetric",
         required=False,
         default=True,
-        type=bool,
+        const=True,
+        nargs="?",
+        type=ort_convert_str_to_bool,
+        choices=[True, False],
         help="Indicate whether to quantize the model symmetrically",
     )
     parser.add_argument(