Hugging Face's logo

qualcomm
/
ConvNext-Tiny

Image Classification
PyTorch
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
6c81c47
·
verified ·
1 Parent(s): 80aa8c2

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +61 -61
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  ConvNextTiny is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
16
 
17
  This is based on the implementation of ConvNext-Tiny found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py).
18
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/convnext_tiny) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
@@ -28,25 +28,25 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.48.0/convnext_tiny-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.48.0/convnext_tiny-onnx-w8a16.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.48.0/convnext_tiny-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.48.0/convnext_tiny-qnn_dlc-w8a16.zip)
35
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.48.0/convnext_tiny-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[ConvNext-Tiny on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/convnext_tiny)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/convnext_tiny) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
- See our repository for [ConvNext-Tiny on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/convnext_tiny) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -62,60 +62,60 @@ See our repository for [ConvNext-Tiny on GitHub](https://github.com/qualcomm/ai-
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | ConvNext-Tiny | ONNX | float | Snapdragon® X2 Elite | 1.344 ms | 57 - 57 MB | NPU
66
- | ConvNext-Tiny | ONNX | float | Snapdragon® X Elite | 2.914 ms | 56 - 56 MB | NPU
67
- | ConvNext-Tiny | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.034 ms | 0 - 168 MB | NPU
68
- | ConvNext-Tiny | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.715 ms | 1 - 106 MB | NPU
69
- | ConvNext-Tiny | ONNX | float | Qualcomm® QCS9075 | 3.947 ms | 0 - 4 MB | NPU
70
- | ConvNext-Tiny | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.554 ms | 0 - 127 MB | NPU
71
- | ConvNext-Tiny | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.278 ms | 0 - 127 MB | NPU
72
- | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® X2 Elite | 1.47 ms | 29 - 29 MB | NPU
73
- | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® X Elite | 2.819 ms | 29 - 29 MB | NPU
74
- | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.798 ms | 0 - 141 MB | NPU
75
- | ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS6490 | 369.385 ms | 50 - 65 MB | CPU
76
- | ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.54 ms | 0 - 38 MB | NPU
77
- | ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS9075 | 2.68 ms | 0 - 3 MB | NPU
78
- | ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCM6690 | 209.914 ms | 60 - 74 MB | CPU
79
- | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.403 ms | 0 - 117 MB | NPU
80
- | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 202.169 ms | 59 - 73 MB | CPU
81
- | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.089 ms | 0 - 115 MB | NPU
82
- | ConvNext-Tiny | QNN_DLC | float | Snapdragon® X2 Elite | 2.041 ms | 1 - 1 MB | NPU
83
- | ConvNext-Tiny | QNN_DLC | float | Snapdragon® X Elite | 3.927 ms | 1 - 1 MB | NPU
84
- | ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.654 ms | 0 - 171 MB | NPU
85
- | ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 15.256 ms | 1 - 124 MB | NPU
86
- | ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.689 ms | 1 - 2 MB | NPU
87
- | ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8775P | 5.004 ms | 1 - 127 MB | NPU
88
- | ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS9075 | 4.876 ms | 1 - 3 MB | NPU
89
- | ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.683 ms | 0 - 168 MB | NPU
90
- | ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA7255P | 15.256 ms | 1 - 124 MB | NPU
91
- | ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8295P | 8.973 ms | 1 - 124 MB | NPU
92
- | ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.027 ms | 0 - 127 MB | NPU
93
- | ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.63 ms | 1 - 127 MB | NPU
94
- | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.614 ms | 0 - 0 MB | NPU
95
- | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® X Elite | 3.409 ms | 0 - 0 MB | NPU
96
- | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.19 ms | 0 - 121 MB | NPU
97
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 9.06 ms | 0 - 2 MB | NPU
98
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 6.854 ms | 0 - 96 MB | NPU
99
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 3.12 ms | 0 - 2 MB | NPU
100
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8775P | 15.078 ms | 0 - 97 MB | NPU
101
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 3.354 ms | 0 - 2 MB | NPU
102
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 23.405 ms | 0 - 250 MB | NPU
103
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 4.273 ms | 0 - 122 MB | NPU
104
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA7255P | 6.854 ms | 0 - 96 MB | NPU
105
- | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8295P | 4.736 ms | 0 - 98 MB | NPU
106
- | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.614 ms | 0 - 98 MB | NPU
107
- | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 3.484 ms | 0 - 107 MB | NPU
108
- | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.283 ms | 0 - 100 MB | NPU
 
109
  | ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.124 ms | 0 - 170 MB | NPU
110
- | ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 13.958 ms | 0 - 122 MB | NPU
111
- | ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.842 ms | 0 - 2 MB | NPU
112
- | ConvNext-Tiny | TFLITE | float | Qualcomm® SA8775P | 4.265 ms | 0 - 122 MB | NPU
113
- | ConvNext-Tiny | TFLITE | float | Qualcomm® QCS9075 | 4.078 ms | 0 - 59 MB | NPU
114
- | ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.864 ms | 0 - 163 MB | NPU
115
- | ConvNext-Tiny | TFLITE | float | Qualcomm® SA7255P | 13.958 ms | 0 - 122 MB | NPU
116
- | ConvNext-Tiny | TFLITE | float | Qualcomm® SA8295P | 7.882 ms | 0 - 118 MB | NPU
117
- | ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.591 ms | 0 - 126 MB | NPU
118
- | ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.299 ms | 0 - 123 MB | NPU
119
 
120
  ## License
121
  * The license for the original implementation of ConvNext-Tiny can be found
 
15
  ConvNextTiny is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
16
 
17
  This is based on the implementation of ConvNext-Tiny found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py).
18
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/convnext_tiny) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.49.1/convnext_tiny-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.49.1/convnext_tiny-onnx-w8a16.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.49.1/convnext_tiny-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.49.1/convnext_tiny-qnn_dlc-w8a16.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny/releases/v0.49.1/convnext_tiny-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[ConvNext-Tiny on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/convnext_tiny)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/convnext_tiny) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
+ See our repository for [ConvNext-Tiny on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/convnext_tiny) for usage instructions.
50
 
51
  ## Model Details
52
 
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
+ | ConvNext-Tiny | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.28 ms | 1 - 126 MB | NPU
66
+ | ConvNext-Tiny | ONNX | float | Snapdragon® X2 Elite | 1.341 ms | 57 - 57 MB | NPU
67
+ | ConvNext-Tiny | ONNX | float | Snapdragon® X Elite | 2.922 ms | 56 - 56 MB | NPU
68
+ | ConvNext-Tiny | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.048 ms | 0 - 170 MB | NPU
69
+ | ConvNext-Tiny | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.703 ms | 1 - 6 MB | NPU
70
+ | ConvNext-Tiny | ONNX | float | Qualcomm® QCS9075 | 3.943 ms | 1 - 4 MB | NPU
71
+ | ConvNext-Tiny | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.552 ms | 0 - 120 MB | NPU
72
+ | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.102 ms | 0 - 115 MB | NPU
73
+ | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® X2 Elite | 1.202 ms | 29 - 29 MB | NPU
74
+ | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® X Elite | 2.839 ms | 29 - 29 MB | NPU
75
+ | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.801 ms | 0 - 141 MB | NPU
76
+ | ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS6490 | 390.543 ms | 49 - 64 MB | CPU
77
+ | ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.506 ms | 0 - 35 MB | NPU
78
+ | ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCS9075 | 2.663 ms | 0 - 3 MB | NPU
79
+ | ConvNext-Tiny | ONNX | w8a16 | Qualcomm® QCM6690 | 209.445 ms | 58 - 71 MB | CPU
80
+ | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.383 ms | 0 - 108 MB | NPU
81
+ | ConvNext-Tiny | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 200.929 ms | 59 - 73 MB | CPU
82
+ | ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.633 ms | 0 - 127 MB | NPU
83
+ | ConvNext-Tiny | QNN_DLC | float | Snapdragon® X2 Elite | 2.005 ms | 1 - 1 MB | NPU
84
+ | ConvNext-Tiny | QNN_DLC | float | Snapdragon® X Elite | 3.945 ms | 1 - 1 MB | NPU
85
+ | ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.649 ms | 0 - 173 MB | NPU
86
+ | ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 15.242 ms | 1 - 124 MB | NPU
87
+ | ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.7 ms | 1 - 3 MB | NPU
88
+ | ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8775P | 5.021 ms | 1 - 126 MB | NPU
89
+ | ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS9075 | 4.878 ms | 1 - 3 MB | NPU
90
+ | ConvNext-Tiny | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.63 ms | 0 - 168 MB | NPU
91
+ | ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA7255P | 15.242 ms | 1 - 124 MB | NPU
92
+ | ConvNext-Tiny | QNN_DLC | float | Qualcomm® SA8295P | 8.975 ms | 1 - 125 MB | NPU
93
+ | ConvNext-Tiny | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.052 ms | 1 - 129 MB | NPU
94
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.281 ms | 0 - 100 MB | NPU
95
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.602 ms | 0 - 0 MB | NPU
96
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® X Elite | 3.395 ms | 0 - 0 MB | NPU
97
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.161 ms | 0 - 121 MB | NPU
98
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 9.075 ms | 2 - 4 MB | NPU
99
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 6.84 ms | 0 - 96 MB | NPU
100
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 3.115 ms | 0 - 2 MB | NPU
101
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8775P | 3.503 ms | 0 - 98 MB | NPU
102
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 3.356 ms | 0 - 2 MB | NPU
103
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 22.414 ms | 0 - 250 MB | NPU
104
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 4.246 ms | 0 - 123 MB | NPU
105
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA7255P | 6.84 ms | 0 - 96 MB | NPU
106
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8295P | 4.74 ms | 0 - 97 MB | NPU
107
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.611 ms | 0 - 98 MB | NPU
108
+ | ConvNext-Tiny | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 3.486 ms | 0 - 107 MB | NPU
109
+ | ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.295 ms | 0 - 126 MB | NPU
110
  | ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.124 ms | 0 - 170 MB | NPU
111
+ | ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 13.979 ms | 0 - 121 MB | NPU
112
+ | ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.84 ms | 0 - 2 MB | NPU
113
+ | ConvNext-Tiny | TFLITE | float | Qualcomm® SA8775P | 4.251 ms | 0 - 123 MB | NPU
114
+ | ConvNext-Tiny | TFLITE | float | Qualcomm® QCS9075 | 4.092 ms | 0 - 59 MB | NPU
115
+ | ConvNext-Tiny | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.905 ms | 0 - 161 MB | NPU
116
+ | ConvNext-Tiny | TFLITE | float | Qualcomm® SA7255P | 13.979 ms | 0 - 121 MB | NPU
117
+ | ConvNext-Tiny | TFLITE | float | Qualcomm® SA8295P | 7.864 ms | 0 - 118 MB | NPU
118
+ | ConvNext-Tiny | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.591 ms | 0 - 124 MB | NPU
 
119
 
120
  ## License
121
  * The license for the original implementation of ConvNext-Tiny can be found