diff --git a/CHANGELOG.rst b/CHANGELOG.rst
index 452f365387..e615627b23 100755
--- a/CHANGELOG.rst
+++ b/CHANGELOG.rst
@@ -13,6 +13,7 @@ NVIDIA Model Optimizer Changelog (Linux)
 - Add standalone type inference option (``--use_standalone_type_inference``) in ONNX AutoCast as an alternative to ONNX's ``infer_shapes``. This experimental feature performs type-only inference without shape inference, useful as a workaround when shape inference fails or to avoid unnecessary shape inference overhead.
 - Add support for Kimi K2 Thinking model quantization from the original int4 checkpoint.
 - Add support for ``params`` constraint based automatic neural architecture search in Minitron pruning (``mcore_minitron``) as an alternative to manual pruning (using ``export_config``). See `examples/pruning/README.md <https://github.com/NVIDIA/Model-Optimizer/tree/main/examples/pruning>`_ for more details on its usage.
+- Add support for calibration data with multiple samples in ``npz`` format in the ONNX Autocast workflow.
 
 0.41 (2026-01-19)
 ^^^^^^^^^^^^^^^^^
diff --git a/modelopt/onnx/autocast/referencerunner.py b/modelopt/onnx/autocast/referencerunner.py
index 8dc91ff089..4d4f9a987c 100644
--- a/modelopt/onnx/autocast/referencerunner.py
+++ b/modelopt/onnx/autocast/referencerunner.py
@@ -30,6 +30,7 @@
 import onnx
 
 from modelopt.onnx.autocast.logging_config import configure_logging, logger
+from modelopt.onnx.quantization.calib_utils import CalibrationDataProvider
 from modelopt.onnx.quantization.ort_utils import _prepare_ep_list
 
 configure_logging()
@@ -70,7 +71,13 @@ def _load_inputs_from_json(self, input_data_path):
 
     def _load_inputs_from_npz(self, input_data_path):
         """Load inputs from NPZ format."""
-        return [np.load(input_data_path)]
+        calib_data = np.load(input_data_path)
+
+        if isinstance(calib_data, np.lib.npyio.NpzFile):
+            # Wrap data into a CalibDataProvider to support a single NPZ file containing data from multiple batches
+            data_loader = {key: calib_data[key] for key in calib_data.files}
+            return CalibrationDataProvider(self.model, data_loader).calibration_data_list
+        return [calib_data]
 
     def _validate_inputs(self, data_loader):
         """Validate that input names and shapes match the model."""
diff --git a/modelopt/onnx/quantization/calib_utils.py b/modelopt/onnx/quantization/calib_utils.py
index e8a538e61c..56e0d4cc01 100644
--- a/modelopt/onnx/quantization/calib_utils.py
+++ b/modelopt/onnx/quantization/calib_utils.py
@@ -38,7 +38,7 @@ class CalibrationDataProvider(CalibrationDataReader):
 
     def __init__(
         self,
-        onnx_path: str,
+        onnx_path: str | onnx.ModelProto,
         calibration_data: CalibrationDataType,
         calibration_shapes: str | None = None,
     ):
@@ -58,7 +58,7 @@ def __init__(
         logger.info("Setting up CalibrationDataProvider for calibration")
         # Tensor data is not required to generate the calibration data
         # So even if the model has external data, we don't need to load them here
-        onnx_model = onnx.load(onnx_path)
+        onnx_model = onnx.load(onnx_path) if isinstance(onnx_path, str) else onnx_path
         input_names = get_input_names(onnx_model)
         input_shapes = {} if calibration_shapes is None else parse_shapes_spec(calibration_shapes)
         inferred_input_shapes = get_input_shapes(onnx_model)