Upload README.md with huggingface_hub

README.md

@@ -36,7 +36,8 @@ 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 | 8.382 ms | 1 - 3 MB | INT8 | NPU |  [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 8.341 ms | 1 - 2 MB | INT8 | NPU |  [FFNet-78S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 5.952 ms | 8 - 26 MB | INT8 | NPU |  [FFNet-78S-Quantized.so](https://huggingface.co/qualcomm/FFNet-78S-Quantized/blob/main/FFNet-78S-Quantized.so) 
 
 
 ## Installation
@@ -97,10 +98,10 @@ python -m qai_hub_models.models.ffnet_78s_quantized.export
 ```
 Profile Job summary of FFNet-78S-Quantized
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 10.68 ms
-Estimated Peak Memory Range: 2.46-4.32 MB
-Compute Units: NPU (156) | Total (156)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 7.10 ms
+Estimated Peak Memory Range: 6.01-6.01 MB
+Compute Units: NPU (146) | Total (146)
 
 
 ```