Upload README.md with huggingface_hub

README.md

@@ -39,8 +39,8 @@ More details on model performance across various devices, can be found
 
 | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
 | ---|---|---|---|---|---|---|---|
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.915 ms | 0 - 1 MB | INT8 | NPU |  [ResNeXt50Quantized.tflite](https://huggingface.co/qualcomm/ResNeXt50Quantized/blob/main/ResNeXt50Quantized.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.169 ms | 0 - 11 MB | INT8 | NPU |  [ResNeXt50Quantized.so](https://huggingface.co/qualcomm/ResNeXt50Quantized/blob/main/ResNeXt50Quantized.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.933 ms | 0 - 6 MB | INT8 | NPU |  [ResNeXt50Quantized.tflite](https://huggingface.co/qualcomm/ResNeXt50Quantized/blob/main/ResNeXt50Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.195 ms | 0 - 62 MB | INT8 | NPU |  [ResNeXt50Quantized.so](https://huggingface.co/qualcomm/ResNeXt50Quantized/blob/main/ResNeXt50Quantized.so) 
 
 
 
@@ -103,8 +103,8 @@ python -m qai_hub_models.models.resnext50_quantized.export
 Profile Job summary of ResNeXt50Quantized
 --------------------------------------------------
 Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 1.41 ms
-Estimated Peak Memory Range: 1.52-1.52 MB
+Estimated Inference Time: 1.24 ms
+Estimated Peak Memory Range: 0.42-0.42 MB
 Compute Units: NPU (78) | Total (78)