Hugging Face's logo

qualcomm
/
ConvNext-Tiny-w8a16-Quantized

Image Classification
PyTorch
ONNX
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
2f7ad69
·
verified ·
1 Parent(s): 73e981d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -36,10 +36,10 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | ConvNext-Tiny | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 90.395 ms | 210 - 371 MB | W8A16 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny.onnx) |
40
- | ConvNext-Tiny | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 87.884 ms | 196 - 533 MB | W8A16 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny.onnx) |
41
- | ConvNext-Tiny | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 64.397 ms | 217 - 518 MB | W8A16 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny.onnx) |
42
- | ConvNext-Tiny | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 90.431 ms | 228 - 228 MB | W8A16 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny.onnx) |
43
 
44
 
45
 
@@ -103,8 +103,8 @@ Profiling Results
103
  ConvNext-Tiny
104
  Device : Samsung Galaxy S23 (13)
105
  Runtime : ONNX
106
- Estimated inference time (ms) : 90.4
107
- Estimated peak memory usage (MB): [210, 371]
108
  Total # Ops : 469
109
  Compute Unit(s) : NPU (429 ops) CPU (40 ops)
110
  ```
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | ConvNext-Tiny | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 94.235 ms | 210 - 363 MB | W8A16 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny.onnx) |
40
+ | ConvNext-Tiny | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 76.704 ms | 213 - 544 MB | W8A16 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny.onnx) |
41
+ | ConvNext-Tiny | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 64.091 ms | 218 - 520 MB | W8A16 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny.onnx) |
42
+ | ConvNext-Tiny | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 88.907 ms | 232 - 232 MB | W8A16 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny.onnx) |
43
 
44
 
45
 
 
103
  ConvNext-Tiny
104
  Device : Samsung Galaxy S23 (13)
105
  Runtime : ONNX
106
+ Estimated inference time (ms) : 94.2
107
+ Estimated peak memory usage (MB): [210, 363]
108
  Total # Ops : 469
109
  Compute Unit(s) : NPU (429 ops) CPU (40 ops)
110
  ```