diff --git a/examples/recipes/README.md b/examples/recipes/README.md
index 86aa01869..1077e4f74 100644
--- a/examples/recipes/README.md
+++ b/examples/recipes/README.md
@@ -38,7 +38,6 @@ Total: **75** (model, task) tuples that pass fp16 eval on all 10 (EP, device) bu
 | ahotrod/electra_large_discriminator_squad2_512 | question-answering |
 | apple/mobilevit-small | image-classification |
 | cardiffnlp/twitter-roberta-base-sentiment-latest | text-classification |
-| cross-encoder/ms-marco-MiniLM-L6-v2 | text-classification |
 | dbmdz/bert-large-cased-finetuned-conll03-english | token-classification |
 | deepset/bert-large-uncased-whole-word-masking-squad2 | question-answering |
 | deepset/roberta-base-squad2 | question-answering |
diff --git a/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/text-classification_w8a16_config.json b/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/cpu/cpu/text-classification_fp16_config.json
similarity index 67%
rename from examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/text-classification_w8a16_config.json
rename to examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/cpu/cpu/text-classification_fp16_config.json
index ce3a2f09e..ca353cc30 100644
--- a/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/text-classification_w8a16_config.json
+++ b/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/cpu/cpu/text-classification_fp16_config.json
@@ -13,38 +13,20 @@
       {
         "name": "input_ids",
         "dtype": "int32",
-        "shape": [
-          1,
-          512
-        ],
-        "value_range": [
-          0,
-          30522
-        ]
+        "shape": [1, 512],
+        "value_range": [0, 30522]
       },
       {
         "name": "attention_mask",
         "dtype": "int32",
-        "shape": [
-          1,
-          512
-        ],
-        "value_range": [
-          0,
-          2
-        ]
+        "shape": [1, 512],
+        "value_range": [0, 2]
       },
       {
         "name": "token_type_ids",
         "dtype": "int32",
-        "shape": [
-          1,
-          512
-        ],
-        "value_range": [
-          0,
-          2
-        ]
+        "shape": [1, 512],
+        "value_range": [0, 2]
       }
     ],
     "output_tensors": [
@@ -53,17 +35,17 @@
       }
     ]
   },
-  "optim": {
-    "clamp_constant_values": true
-  },
+  "optim": {},
   "quant": {
-    "mode": "qdq",
+    "mode": "fp16",
     "samples": 10,
     "calibration_method": "minmax",
     "weight_type": "uint8",
-    "activation_type": "uint16",
+    "activation_type": "uint8",
     "per_channel": false,
     "symmetric": false,
+    "weight_symmetric": null,
+    "activation_symmetric": null,
     "save_calibration": false,
     "distribution": "uniform",
     "seed": null,
@@ -71,8 +53,8 @@
     "calibration_save_path": null,
     "op_types_to_quantize": null,
     "nodes_to_exclude": null,
-    "task": "text-classification",
-    "model_id": "cross-encoder/ms-marco-MiniLM-L6-v2"
+    "fp16_keep_io_types": true,
+    "fp16_op_block_list": null
   },
   "compile": null,
   "loader": {
diff --git a/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/text-classification_fp16_config.json b/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/cpu/cpu/text-classification_fp32_config.json
similarity index 65%
rename from examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/text-classification_fp16_config.json
rename to examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/cpu/cpu/text-classification_fp32_config.json
index b8612e5ac..eb9f77384 100644
--- a/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/text-classification_fp16_config.json
+++ b/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/cpu/cpu/text-classification_fp32_config.json
@@ -13,38 +13,20 @@
       {
         "name": "input_ids",
         "dtype": "int32",
-        "shape": [
-          1,
-          512
-        ],
-        "value_range": [
-          0,
-          30522
-        ]
+        "shape": [1, 512],
+        "value_range": [0, 30522]
       },
       {
         "name": "attention_mask",
         "dtype": "int32",
-        "shape": [
-          1,
-          512
-        ],
-        "value_range": [
-          0,
-          2
-        ]
+        "shape": [1, 512],
+        "value_range": [0, 2]
       },
       {
         "name": "token_type_ids",
         "dtype": "int32",
-        "shape": [
-          1,
-          512
-        ],
-        "value_range": [
-          0,
-          2
-        ]
+        "shape": [1, 512],
+        "value_range": [0, 2]
       }
     ],
     "output_tensors": [
@@ -53,9 +35,7 @@
       }
     ]
   },
-  "optim": {
-    "clamp_constant_values": true
-  },
+  "optim": {},
   "quant": null,
   "compile": null,
   "loader": {
diff --git a/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/dml/gpu/text-classification_fp16_config.json b/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/dml/gpu/text-classification_fp16_config.json
new file mode 100644
index 000000000..ca353cc30
--- /dev/null
+++ b/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/dml/gpu/text-classification_fp16_config.json
@@ -0,0 +1,65 @@
+{
+  "export": {
+    "opset_version": 17,
+    "batch_size": 1,
+    "export_params": true,
+    "do_constant_folding": true,
+    "verbose": false,
+    "dynamo": false,
+    "enable_hierarchy_tags": true,
+    "clean_onnx": false,
+    "hierarchy_tag_format": "full",
+    "input_tensors": [
+      {
+        "name": "input_ids",
+        "dtype": "int32",
+        "shape": [1, 512],
+        "value_range": [0, 30522]
+      },
+      {
+        "name": "attention_mask",
+        "dtype": "int32",
+        "shape": [1, 512],
+        "value_range": [0, 2]
+      },
+      {
+        "name": "token_type_ids",
+        "dtype": "int32",
+        "shape": [1, 512],
+        "value_range": [0, 2]
+      }
+    ],
+    "output_tensors": [
+      {
+        "name": "logits"
+      }
+    ]
+  },
+  "optim": {},
+  "quant": {
+    "mode": "fp16",
+    "samples": 10,
+    "calibration_method": "minmax",
+    "weight_type": "uint8",
+    "activation_type": "uint8",
+    "per_channel": false,
+    "symmetric": false,
+    "weight_symmetric": null,
+    "activation_symmetric": null,
+    "save_calibration": false,
+    "distribution": "uniform",
+    "seed": null,
+    "calibration_load_path": null,
+    "calibration_save_path": null,
+    "op_types_to_quantize": null,
+    "nodes_to_exclude": null,
+    "fp16_keep_io_types": true,
+    "fp16_op_block_list": null
+  },
+  "compile": null,
+  "loader": {
+    "task": "text-classification",
+    "model_class": "AutoModelForSequenceClassification",
+    "model_type": "bert"
+  }
+}
diff --git a/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/dml/gpu/text-classification_fp32_config.json b/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/dml/gpu/text-classification_fp32_config.json
new file mode 100644
index 000000000..eb9f77384
--- /dev/null
+++ b/examples/recipes/cross-encoder_ms-marco-MiniLM-L6-v2/dml/gpu/text-classification_fp32_config.json
@@ -0,0 +1,46 @@
+{
+  "export": {
+    "opset_version": 17,
+    "batch_size": 1,
+    "export_params": true,
+    "do_constant_folding": true,
+    "verbose": false,
+    "dynamo": false,
+    "enable_hierarchy_tags": true,
+    "clean_onnx": false,
+    "hierarchy_tag_format": "full",
+    "input_tensors": [
+      {
+        "name": "input_ids",
+        "dtype": "int32",
+        "shape": [1, 512],
+        "value_range": [0, 30522]
+      },
+      {
+        "name": "attention_mask",
+        "dtype": "int32",
+        "shape": [1, 512],
+        "value_range": [0, 2]
+      },
+      {
+        "name": "token_type_ids",
+        "dtype": "int32",
+        "shape": [1, 512],
+        "value_range": [0, 2]
+      }
+    ],
+    "output_tensors": [
+      {
+        "name": "logits"
+      }
+    ]
+  },
+  "optim": {},
+  "quant": null,
+  "compile": null,
+  "loader": {
+    "task": "text-classification",
+    "model_class": "AutoModelForSequenceClassification",
+    "model_type": "bert"
+  }
+}