diff --git a/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/README.md b/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/README.md
index 0af1ba5c9cf..bbcc0ee7a72 100644
--- a/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/README.md
+++ b/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/README.md
@@ -1,5 +1,5 @@
 # MiniCPM-V-2_6
-In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on MiniCPM-V-2_6 model on [Intel GPUs](../../../README.md). For illustration purposes, we utilize [openbmb/MiniCPM-V-2_6](https://huggingface.co/openbmb/MiniCPM-V-2_6) as reference MiniCPM-V-2_6 model.
+In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on MiniCPM-V-2_6 model on [Intel GPUs](../../../README.md). For illustration purposes, we utilize [openbmb/MiniCPM-V-2_6](https://huggingface.co/openbmb/MiniCPM-V-2_6) (or [OpenBMB/MiniCPM-V-2_6](https://www.modelscope.cn/models/OpenBMB/MiniCPM-V-2_6) for ModelScope) as reference MiniCPM-V-2_6 model.
 
 ## 0. Requirements
 To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information.
@@ -16,6 +16,9 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
 pip install transformers==4.40.0 "trl<0.12.0"
+
+# [optional] only needed if you would like to use ModelScope as model hub
+pip install modelscope==1.11.0
 ```
 
 #### 1.2 Installation on Windows
@@ -28,6 +31,9 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
 pip install transformers==4.40.0 "trl<0.12.0"
+
+# [optional] only needed if you would like to use ModelScope as model hub
+pip install modelscope==1.11.0
 ```
 
 ### 2. Configures OneAPI environment variables for Linux
@@ -96,31 +102,48 @@ set SYCL_CACHE_PERSISTENT=1
 ### 4. Running examples
 
 - chat without streaming mode:
-  ```
+  ```bash
+  # for Hugging Face model hub
   python ./chat.py --prompt 'What is in the image?'
+
+  # for ModelScope model hub
+  python ./chat.py --prompt 'What is in the image?' --modelscope
   ```
 - chat in streaming mode:
-  ```
+  ```bash
+  # for Hugging Face model hub
   python ./chat.py --prompt 'What is in the image?' --stream
+
+  # for ModelScope model hub
+  python ./chat.py --prompt 'What is in the image?' --stream --modelscope
   ```
 - save model with low-bit optimization (if `LOWBIT_MODEL_PATH` does not exist)
-  ```
+  ```bash
+  # for Hugging Face model hub
   python ./chat.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --lowbit-path LOWBIT_MODEL_PATH --prompt 'What is in the image?'
+
+  # for ModelScope model hub
+  python ./chat.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --lowbit-path LOWBIT_MODEL_PATH --prompt 'What is in the image?' --modelscope
   ```
 - chat with saved model with low-bit optimization (if `LOWBIT_MODEL_PATH` exists):
-  ```
+  ```bash
+  # for Hugging Face model hub
   python ./chat.py --lowbit-path LOWBIT_MODEL_PATH --prompt 'What is in the image?'
+
+  # for ModelScope model hub
+  python ./chat.py --lowbit-path LOWBIT_MODEL_PATH --prompt 'What is in the image?' --modelscope
   ```
 
 > [!TIP]
 > For chatting in streaming mode, it is recommended to set the environment variable `PYTHONUNBUFFERED=1`.
 
 Arguments info:
-- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the MiniCPM-V-2_6 (e.g. `openbmb/MiniCPM-V-2_6`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'openbmb/MiniCPM-V-2_6'`.
+- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the **Hugging Face** or **ModelScope** repo id for the MiniCPM-V-2_6 (e.g. `openbmb/MiniCPM-V-2_6`) to be downloaded, or the path to the checkpoint folder. It is default to be `'openbmb/MiniCPM-V-2_6'` for **Hugging Face** or `'OpenBMB/MiniCPM-V-2_6'` for **ModelScope**.
 - `--lowbit-path LOWBIT_MODEL_PATH`: argument defining the path to save/load the model with IPEX-LLM low-bit optimization. If it is an empty string, the original pretrained model specified by `REPO_ID_OR_MODEL_PATH` will be loaded. If it is an existing path, the saved model with low-bit optimization in `LOWBIT_MODEL_PATH` will be loaded. If it is a non-existing path, the original pretrained model specified by `REPO_ID_OR_MODEL_PATH` will be loaded, and the optimized low-bit model will be saved into `LOWBIT_MODEL_PATH`. It is default to be `''`, i.e. an empty string.
 - `--image-url-or-path IMAGE_URL_OR_PATH`: argument defining the image to be infered. It is default to be `'http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg'`.
 - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'What is in the image?'`.
 - `--stream`: flag to chat in streaming mode
+- `--modelscope`: using **ModelScope** as model hub instead of **Hugging Face**.
 
 #### Sample Output
 
diff --git a/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/chat.py b/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/chat.py
index cad68239fd5..bcfc4fda40f 100644
--- a/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/chat.py
+++ b/python/llm/example/GPU/HuggingFace/Multimodal/MiniCPM-V-2_6/chat.py
@@ -22,14 +22,13 @@
 import torch
 from PIL import Image
 from ipex_llm.transformers import AutoModel
-from transformers import AutoTokenizer, AutoProcessor
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Predict Tokens using `chat()` API for openbmb/MiniCPM-V-2_6 model')
-    parser.add_argument('--repo-id-or-model-path', type=str, default="openbmb/MiniCPM-V-2_6",
-                        help='The huggingface repo id for the openbmb/MiniCPM-V-2_6 model to be downloaded'
-                             ', or the path to the huggingface checkpoint folder')
+    parser.add_argument('--repo-id-or-model-path', type=str,
+                        help='The Hugging Face or ModelScope repo id for the MiniCPM-V-2_6 model to be downloaded'
+                             ', or the path to the checkpoint folder')
     parser.add_argument("--lowbit-path", type=str,
         default="",
         help="The path to the saved model folder with IPEX-LLM low-bit optimization. "
@@ -44,9 +43,20 @@
                         help='Prompt to infer')
     parser.add_argument('--stream', action='store_true',
                         help='Whether to chat in streaming mode')
+    parser.add_argument('--modelscope', action="store_true", default=False, 
+                        help="Use models from modelscope")
 
     args = parser.parse_args()
-    model_path = args.repo_id_or_model_path
+
+    if args.modelscope:
+        from modelscope import AutoTokenizer, AutoProcessor
+        model_hub = 'modelscope'
+    else:
+        from transformers import AutoTokenizer, AutoProcessor
+        model_hub = 'huggingface'
+    
+    model_path = args.repo_id_or_model_path if args.repo_id_or_model_path else \
+        ("OpenBMB/MiniCPM-V-2_6" if args.modelscope else "openbmb/MiniCPM-V-2_6")
     image_path = args.image_url_or_path
 
     lowbit_path = args.lowbit_path
@@ -61,7 +71,8 @@
                                         optimize_model=True,
                                         trust_remote_code=True,
                                         use_cache=True,
-                                        modules_to_not_convert=["vpm", "resampler"])
+                                        modules_to_not_convert=["vpm", "resampler"],
+                                        model_hub=model_hub)
 
         tokenizer = AutoTokenizer.from_pretrained(model_path,
                                                   trust_remote_code=True)
@@ -70,7 +81,8 @@
                                        optimize_model=True,
                                        trust_remote_code=True,
                                        use_cache=True,
-                                       modules_to_not_convert=["vpm", "resampler"])
+                                       modules_to_not_convert=["vpm", "resampler"],
+                                       model_hub=model_hub)
         tokenizer = AutoTokenizer.from_pretrained(lowbit_path,
                                                   trust_remote_code=True)
     
diff --git a/python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/README.md b/python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/README.md
index 7464c7e7751..3720b05983b 100644
--- a/python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/README.md
+++ b/python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/README.md
@@ -1,5 +1,5 @@
 # GLM-4V
-In this directory, you will find examples on how you could apply IPEX-LLM FP8 optimizations on GLM-4V models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [THUDM/glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b) as a reference GLM-4V model.
+In this directory, you will find examples on how you could apply IPEX-LLM FP8 optimizations on GLM-4V models on [Intel GPUs](../../../README.md). For illustration purposes, we utilize the [THUDM/glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b) (or [ZhipuAI/glm-4v-9b](https://www.modelscope.cn/models/ZhipuAI/glm-4v-9b) for ModelScope) as a reference GLM-4V model.
 
 ## 0. Requirements
 To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to [here](../../../README.md#requirements) for more information.
@@ -16,6 +16,9 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
 pip install tiktoken transformers==4.42.4 "trl<0.12.0"
+
+# [optional] only needed if you would like to use ModelScope as model hub
+pip install modelscope==1.11.0
 ```
 
 #### 1.2 Installation on Windows
@@ -28,6 +31,9 @@ conda activate llm
 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
 
 pip install tiktoken transformers==4.42.4 "trl<0.12.0"
+
+# [optional] only needed if you would like to use ModelScope as model hub
+pip install modelscope==1.11.0
 ```
 
 ### 2. Configures OneAPI environment variables for Linux
@@ -95,15 +101,20 @@ set SYCL_CACHE_PERSISTENT=1
 > For the first time that each model runs on Intel iGPU/Intel Arc™ A300-Series or Pro A60, it may take several minutes to compile.
 ### 4. Running examples
 
-```
-python ./generate.py --prompt 'What is in the image?'
+```bash
+# for Hugging Face model hub
+python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT --image-url-or-path IMAGE_URL_OR_PATH
+
+# for ModelScope model hub
+python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT --image-url-or-path IMAGE_URL_OR_PATH --modelscope
 ```
 
 Arguments info:
-- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the huggingface repo id for the GLM-4V model (e.g. `THUDM/glm-4v-9b`) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be `'THUDM/glm-4v-9b'`.
+- `--repo-id-or-model-path REPO_ID_OR_MODEL_PATH`: argument defining the **Hugging Face** or **ModelScope** repo id for the GLM-4V model (e.g. `THUDM/glm-4v-9b`) to be downloaded, or the path to the checkpoint folder. It is default to be `'THUDM/glm-4v-9b'` for **Hugging Face** or `'ZhipuAI/glm-4v-9b'` for **ModelScope**.
 - `--image-url-or-path IMAGE_URL_OR_PATH`: argument defining the image to be infered. It is default to be `'http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg'`.
 - `--prompt PROMPT`: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be `'What is in the image?'`.
 - `--n-predict N_PREDICT`: argument defining the max number of tokens to predict. It is default to be `32`.
+- `--modelscope`: using **ModelScope** as model hub instead of **Hugging Face**.
 
 #### Sample Output
 #### [THUDM/glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b)
diff --git a/python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/generate.py b/python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/generate.py
index 6a1dd035e9e..1ac3cdbf690 100644
--- a/python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/generate.py
+++ b/python/llm/example/GPU/HuggingFace/Multimodal/glm-4v/generate.py
@@ -22,13 +22,12 @@
 
 from PIL import Image
 from ipex_llm.transformers import AutoModelForCausalLM
-from transformers import AutoTokenizer
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Predict Tokens using `generate()` API for THUDM/glm-4v-9b model')
-    parser.add_argument('--repo-id-or-model-path', type=str, default="THUDM/glm-4v-9b",
-                        help='The huggingface repo id for the THUDM/glm-4v-9b model to be downloaded'
-                             ', or the path to the huggingface checkpoint folder')
+    parser.add_argument('--repo-id-or-model-path', type=str,
+                        help='The Hugging Face or ModelScope repo id for the glm-4v model to be downloaded'
+                             ', or the path to the checkpoint folder')
     parser.add_argument('--image-url-or-path', type=str,
                         default='http://farm6.staticflickr.com/5268/5602445367_3504763978_z.jpg',
                         help='The URL or path to the image to infer')
@@ -36,9 +35,20 @@
                         help='Prompt to infer')
     parser.add_argument('--n-predict', type=int, default=32,
                         help='Max tokens to predict')
+    parser.add_argument('--modelscope', action="store_true", default=False, 
+                        help="Use models from modelscope")
 
     args = parser.parse_args()
-    model_path = args.repo_id_or_model_path
+
+    if args.modelscope:
+        from modelscope import AutoTokenizer
+        model_hub = 'modelscope'
+    else:
+        from transformers import AutoTokenizer
+        model_hub = 'huggingface'
+    
+    model_path = args.repo_id_or_model_path if args.repo_id_or_model_path else \
+        ("ZhipuAI/glm-4v-9b" if args.modelscope else "THUDM/glm-4v-9b")
     image_path = args.image_url_or_path
     
     # Load model in 4 bit,
@@ -49,7 +59,9 @@
                                                  load_in_4bit=True,
                                                  optimize_model=True,
                                                  trust_remote_code=True,
-                                                 use_cache=True).half().to('xpu')
+                                                 use_cache=True,
+                                                 model_hub=model_hub)
+    model = model.half().to('xpu')
     
     tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)