Hugging Face's logo

qualcomm
/
EfficientNet-V2-s

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
ac3ed02
·
verified ·
1 Parent(s): 34093cd

v0.42.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.42.0 for changelog.

Files changed (5) hide show
  1. EfficientNet-V2-s_float.dlc +2 -2
  2. EfficientNet-V2-s_float.onnx.zip +1 -1
  3. EfficientNet-V2-s_w8a16.dlc +2 -2
  4. EfficientNet-V2-s_w8a16.onnx.zip +2 -2
  5. README.md +42 -40
EfficientNet-V2-s_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fe923f2320564d8e0988e1f60651c24aa32e85e102c1ed0aae90450a5991812
3
- size 86057540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70693833028ee6c7680204a691db531abc52633282e567f4d1ba9d8f2781cd6
3
+ size 86057644
EfficientNet-V2-s_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42e5ce8f1a9d5236895c970723cdfa275d49879f71ee7f9f1b21ab2f89cf83ed
3
  size 79809736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a2461748104060a4491f2b24d524c423772e3630244f4418e06c482d175f02
3
  size 79809736
EfficientNet-V2-s_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ef23332449cba1b56fbc3599859d5a86b92222b6e7d76921c1aefc651caf3a2
3
- size 28565460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825172a50a5b5f6d33846f6aa7bd7a64fe1df248de3249295850aca202a80b3d
3
+ size 28565564
EfficientNet-V2-s_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84e5479b98f24991246e8deb47a84c13ff52920695861cae2fd3bfb14faf2943
3
- size 44581656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c7f699bae9b654420d8be214226a0e1aacb1acf5d44325dc0add4543def617
3
+ size 44583654
README.md CHANGED
@@ -38,42 +38,44 @@ More details on model performance across various devices, can be found
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
- | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 11.004 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
42
- | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 10.814 ms | 0 - 34 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
43
- | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.865 ms | 0 - 90 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
44
- | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.542 ms | 1 - 44 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
45
- | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.724 ms | 0 - 364 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
46
- | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.565 ms | 0 - 15 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
47
- | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.646 ms | 0 - 109 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
48
- | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3.867 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
49
- | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.709 ms | 1 - 35 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
50
- | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.986 ms | 0 - 107 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
51
- | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.904 ms | 1 - 65 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
52
- | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.948 ms | 0 - 70 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
53
- | EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1.569 ms | 0 - 81 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
54
- | EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.491 ms | 1 - 41 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
55
- | EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.588 ms | 0 - 42 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
56
- | EfficientNet-V2-s | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1.277 ms | 0 - 81 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
57
- | EfficientNet-V2-s | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.227 ms | 1 - 41 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
58
- | EfficientNet-V2-s | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1.358 ms | 1 - 42 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
59
- | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.865 ms | 217 - 217 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
60
- | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.69 ms | 47 - 47 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
61
- | EfficientNet-V2-s | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.362 ms | 0 - 66 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
62
- | EfficientNet-V2-s | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 3.215 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
63
- | EfficientNet-V2-s | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.62 ms | 0 - 22 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
64
- | EfficientNet-V2-s | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.714 ms | 0 - 50 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
65
- | EfficientNet-V2-s | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.996 ms | 0 - 65 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
66
- | EfficientNet-V2-s | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 9.397 ms | 0 - 124 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
67
- | EfficientNet-V2-s | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 131.694 ms | 24 - 46 MB | CPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
68
- | EfficientNet-V2-s | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 128.347 ms | 19 - 33 MB | CPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
69
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.784 ms | 0 - 78 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
70
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.8 ms | 0 - 83 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
71
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.246 ms | 0 - 71 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
72
- | EfficientNet-V2-s | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.384 ms | 0 - 76 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
73
- | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.021 ms | 0 - 71 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
74
- | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1.148 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
75
- | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.918 ms | 100 - 100 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
76
- | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.729 ms | 26 - 26 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
 
 
77
 
78
 
79
 
@@ -87,9 +89,9 @@ pip install qai-hub-models
87
  ```
88
 
89
 
90
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
91
 
92
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
93
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
94
 
95
  With this API token, you can configure your client to run models on the cloud
@@ -97,7 +99,7 @@ hosted devices.
97
  ```bash
98
  qai-hub configure --api_token API_TOKEN
99
  ```
100
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
101
 
102
 
103
 
@@ -208,7 +210,7 @@ With the output of the model, you can compute like PSNR, relative errors or
208
  spot check the output with expected output.
209
 
210
  **Note**: This on-device profiling and inference requires access to Qualcomm®
211
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
212
 
213
 
214
 
 
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
+ | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 11.061 ms | 0 - 79 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
42
+ | EfficientNet-V2-s | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 10.795 ms | 0 - 35 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
43
+ | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.921 ms | 0 - 93 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
44
+ | EfficientNet-V2-s | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.503 ms | 1 - 47 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
45
+ | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.691 ms | 0 - 375 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
46
+ | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.571 ms | 0 - 86 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
47
+ | EfficientNet-V2-s | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.723 ms | 1 - 13 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
48
+ | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 3.833 ms | 0 - 79 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
49
+ | EfficientNet-V2-s | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.689 ms | 1 - 36 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
50
+ | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.994 ms | 0 - 107 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
51
+ | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.882 ms | 1 - 66 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
52
+ | EfficientNet-V2-s | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.934 ms | 0 - 68 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
53
+ | EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1.567 ms | 0 - 83 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
54
+ | EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.483 ms | 1 - 43 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
55
+ | EfficientNet-V2-s | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.59 ms | 0 - 42 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
56
+ | EfficientNet-V2-s | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 1.283 ms | 0 - 82 MB | NPU | [EfficientNet-V2-s.tflite](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.tflite) |
57
+ | EfficientNet-V2-s | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 1.229 ms | 1 - 41 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
58
+ | EfficientNet-V2-s | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1.363 ms | 1 - 44 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
59
+ | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.855 ms | 212 - 212 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.dlc) |
60
+ | EfficientNet-V2-s | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.657 ms | 47 - 47 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s.onnx.zip) |
61
+ | EfficientNet-V2-s | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.374 ms | 0 - 66 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
62
+ | EfficientNet-V2-s | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 3.25 ms | 0 - 76 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
63
+ | EfficientNet-V2-s | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.605 ms | 0 - 18 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
64
+ | EfficientNet-V2-s | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 2.75 ms | 0 - 24 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
65
+ | EfficientNet-V2-s | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 3.007 ms | 0 - 65 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
66
+ | EfficientNet-V2-s | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 9.327 ms | 0 - 125 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
67
+ | EfficientNet-V2-s | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 131.559 ms | 23 - 44 MB | CPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
68
+ | EfficientNet-V2-s | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 120.599 ms | 22 - 31 MB | CPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
69
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.773 ms | 0 - 79 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
70
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.801 ms | 0 - 85 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
71
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.221 ms | 0 - 74 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
72
+ | EfficientNet-V2-s | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 1.388 ms | 0 - 76 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
73
+ | EfficientNet-V2-s | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 3.056 ms | 0 - 70 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
74
+ | EfficientNet-V2-s | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 132.574 ms | 25 - 45 MB | CPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
75
+ | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.99 ms | 0 - 73 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
76
+ | EfficientNet-V2-s | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 1.173 ms | 0 - 77 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
77
+ | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.91 ms | 102 - 102 MB | NPU | [EfficientNet-V2-s.dlc](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.dlc) |
78
+ | EfficientNet-V2-s | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.733 ms | 25 - 25 MB | NPU | [EfficientNet-V2-s.onnx.zip](https://huggingface.co/qualcomm/EfficientNet-V2-s/blob/main/EfficientNet-V2-s_w8a16.onnx.zip) |
79
 
80
 
81
 
 
89
  ```
90
 
91
 
92
+ ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
93
 
94
+ Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
95
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
96
 
97
  With this API token, you can configure your client to run models on the cloud
 
99
  ```bash
100
  qai-hub configure --api_token API_TOKEN
101
  ```
102
+ Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
103
 
104
 
105
 
 
210
  spot check the output with expected output.
211
 
212
  **Note**: This on-device profiling and inference requires access to Qualcomm®
213
+ AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
214
 
215
 
216