diff --git a/Demos/Multi-model/README.md b/Demos/Multi-model/README.md
new file mode 100644
index 00000000..dea320fe
--- /dev/null
+++ b/Demos/Multi-model/README.md
@@ -0,0 +1,60 @@
+<table class="sphinxhide" width="100%">
+ <tr width="100%">
+    <td align="center"><img src="https://raw.githubusercontent.com/Xilinx/Image-Collateral/main/xilinx-logo.png" width="30%"/><h1> Ryzen™ AI Multi model demo </h1>
+    </td>
+ </tr>
+</table>
+
+# Multi Model Running on NPU
+
+We showcase an application that loads 2 different models in a single thread.
+
+```text
+NOTE: Models has to be initiated in proper order. The largest model needs to be initiated first.
+```
+
+## Prerequisites and Environment Setup
+
+Install Ryzen AI Software using the automatic installer [Link](https://ryzenai.docs.amd.com/en/latest/inst.html). This should create a  conda environment that can be used for this example. Check the installation path variables
+
+Below instructions can be executed on Conda command prompt or Miniforge Prompt
+
+1. Create a clone of the Ryzen AI installation conda environment to add required python packages
+
+```python
+set RYZEN_AI_CONDA_ENV_NAME=ryzen-ai-<version>
+conda create --name npu-gpu-pipeline --clone %RYZEN_AI_CONDA_ENV_NAME%
+conda activate npu-gpu-pipeline
+```
+2. Set RyzenAI Environment variable
+
+```bash
+# Location of RyzenAI software installation path or default at "C:\Program Files\RyzenAI\<version>"
+set RYZEN_AI_INSTALLATION_PATH=<Path to RyzenAI Installation>
+```
+
+3. Additional configuration needed.
+
+```text
+   Running of multi models in a single app needs additional setup.
+   Models has to be initiated in proper order. The largest model needs to be initiated first.
+   Also maxSpillBufferSize (in bytes) in provider_options should be bigger than the largest model.
+   Please check compile_multi_model.py for reference.
+```
+
+## Prepare models
+Download ResNet50 and Mobilenet_v2 models
+
+```bash
+cd models
+python download_2_models.py
+```
+
+## Running the application
+
+1. Run the example:
+
+```bash
+cd ..
+python compile_multi_model.py
+```
diff --git a/Demos/Multi-model/compile_multi_model.py b/Demos/Multi-model/compile_multi_model.py
new file mode 100755
index 00000000..e41ea013
--- /dev/null
+++ b/Demos/Multi-model/compile_multi_model.py
@@ -0,0 +1,28 @@
+import onnxruntime as ort
+
+#   Model               -   size
+# mobilenet_v2.onnx     - 25153280
+# resnet50.onnx         - 12548096
+
+print("Init the largest model on top");
+provider_options = [{
+    'config_file': 'vaiml_config.json',
+    'cache_dir': 'models_cache',
+    'cache_key': 'model1',
+    'maxSpillBufferSize': "26000000", # 26MB Larger than the largest model
+    "enable_cache_file_io_in_mem": "0"
+}]
+
+s1 = ort.InferenceSession("models/mobilenet_v2.onnx", providers=['VitisAIExecutionProvider'], provider_options=provider_options)
+
+
+print("Init smaller models below");
+provider_options = [{
+    'config_file': 'vaiml_config.json',
+    'cache_dir': 'models_cache',
+    'cache_key': 'model2',
+    'maxSpillBufferSize': "26000000", # 26MB Larger than the largest model
+    "enable_cache_file_io_in_mem": "0"
+}]
+
+s2 = ort.InferenceSession("models/resnet50.onnx", providers=['VitisAIExecutionProvider'], provider_options=provider_options)
diff --git a/Demos/Multi-model/models/download_2_models.py b/Demos/Multi-model/models/download_2_models.py
new file mode 100644
index 00000000..f8bbf48c
--- /dev/null
+++ b/Demos/Multi-model/models/download_2_models.py
@@ -0,0 +1,44 @@
+import torch
+import torchvision.models as models
+import torch.onnx
+from torchvision.models import resnet50, ResNet50_Weights
+import onnx
+
+# Load a pre-trained ResNet model
+model = models.resnet50(weights=ResNet50_Weights.DEFAULT)
+model.eval()  # Set the model to evaluation mode
+
+# Create a dummy input tensor with the same size as the model's input
+dummy_input = torch.randn(1, 3, 224, 224)
+
+onnx_model_path = "resnet50.onnx"
+
+# Export the model to ONNX format
+torch.onnx.export(
+    model,
+    dummy_input,
+    onnx_model_path,
+    opset_version=17,
+    export_params=True,
+    input_names=['input'],
+    output_names=['output'],
+    dynamic_axes={'input': {0: 'batch_size'}, 'output': {0: 'batch_size'}}
+)
+
+mobilenet_v2_model_path = "mobilenet_v2.onnx"
+mobilenet_v2 = models.mobilenet_v2(pretrained=True)
+mobilenet_v2.eval()
+
+torch.onnx.export(
+    mobilenet_v2,
+    dummy_input,
+    mobilenet_v2_model_path,
+    export_params=True,
+    opset_version=17,
+    do_constant_folding=True,
+    input_names=["input"],
+    output_names=["output"],
+    dynamic_axes={"input": {0: "batch"}, "output": {0: "batch"}}
+)
+
+print(f"Models has been successfully exported to {onnx_model_path} and {mobilenet_v2_model_path}")
diff --git a/Demos/Multi-model/vaiml_config.json b/Demos/Multi-model/vaiml_config.json
new file mode 100644
index 00000000..d09b13e9
--- /dev/null
+++ b/Demos/Multi-model/vaiml_config.json
@@ -0,0 +1,26 @@
+{
+    "passes": [
+        {
+            "name": "init",
+            "plugin": "vaip-pass_init"
+        },
+        {
+            "name": "vaiml_partition",
+            "plugin": "vaip-pass_vaiml_partition",
+            "vaiml_config": {
+                "enable_f32_to_bf16_conversion": true,
+                "preferred_data_storage": "auto"
+        }
+        }
+    ],
+    "target": "VAIML",
+    "targets": [
+        {
+            "name": "VAIML",
+            "pass": [
+                "init",
+                "vaiml_partition"
+            ]
+        }
+    ]
+  }