Hugging Face's logo

qualcomm
/
EfficientFormer

Image Classification
PyTorch
LiteRT
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
77634dd
·
verified ·
1 Parent(s): e733630

v0.44.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.44.0 for changelog.

Files changed (8) hide show
  1. DEPLOYMENT_MODEL_LICENSE.pdf +0 -3
  2. EfficientFormer_float.dlc +1 -1
  3. EfficientFormer_float.onnx.zip +2 -2
  4. EfficientFormer_float.tflite +2 -2
  5. EfficientFormer_w8a16.dlc +1 -1
  6. EfficientFormer_w8a16.onnx.zip +2 -2
  7. LICENSE +0 -1
  8. README.md +39 -37
DEPLOYMENT_MODEL_LICENSE.pdf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
- size 109629
 
 
 
 
EfficientFormer_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3e93cf5d7197bc3d5c487642389bef76379ce3e2f9cb56c35461accd448d935
3
  size 49274172
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8fc050890aef92f7c13ac1d28dad913c3b301ca2e17a4ac0b66ddad93d3f84
3
  size 49274172
EfficientFormer_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba3155215eae64f80beb32274350204064c97597ff4be2d331fdd3d042f4261a
3
- size 45831792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88528867cce78e62298411f2c59fd2b6944651427a6e4294cbec303f73517a92
3
+ size 45831693
EfficientFormer_float.tflite CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d87b3fab318a4ea699fa72477cbfb31bafc738c3af67139f179af0047cae6a87
3
- size 49132840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885a7277249d33f7129cfe8dc2d170016a500e770bae8bd31fd4c912205e2556
3
+ size 49132860
EfficientFormer_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdb64093fd3a009a7e8332e031534a6abca864c07d225d6dcc7dbfaa91561538
3
  size 13565404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca4949ab0a4d335001cbdaa6ab0d999ac2f0f035f580e59bdb3afc75cf9d708
3
  size 13565404
EfficientFormer_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ff05d8caca1b94abcbfef38bf3fe1ba9670db2d9faccbf33f3f35afa6ecbe54
3
- size 27609124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d2ff1a8f1d2ed171e9e526b4e660d2d29c4527f2b5dde8306dda35c3dd4297d
3
+ size 27609155
LICENSE CHANGED
@@ -1,2 +1 @@
1
  The license of the original trained model can be found at https://github.com/snap-research/EfficientFormer?tab=License-1-ov-file#readme.
2
- The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
 
1
  The license of the original trained model can be found at https://github.com/snap-research/EfficientFormer?tab=License-1-ov-file#readme.
 
README.md CHANGED
@@ -2,6 +2,7 @@
2
  library_name: pytorch
3
  license: other
4
  tags:
 
5
  - android
6
  pipeline_tag: image-classification
7
 
@@ -36,42 +37,44 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | EfficientFormer | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 4.978 ms | 0 - 49 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
40
- | EfficientFormer | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 4.984 ms | 1 - 35 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
41
- | EfficientFormer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 3.868 ms | 0 - 59 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
42
- | EfficientFormer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.607 ms | 1 - 47 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
43
- | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.521 ms | 0 - 169 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
44
- | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.603 ms | 1 - 9 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
45
- | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 1.603 ms | 0 - 66 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
46
- | EfficientFormer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2.135 ms | 0 - 50 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
47
- | EfficientFormer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.218 ms | 0 - 34 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
48
- | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.072 ms | 0 - 58 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
49
- | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.11 ms | 1 - 43 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
50
- | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.103 ms | 0 - 42 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
51
- | EfficientFormer | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.818 ms | 0 - 56 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
52
- | EfficientFormer | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.82 ms | 1 - 40 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
53
- | EfficientFormer | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 0.904 ms | 0 - 36 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
54
- | EfficientFormer | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.725 ms | 0 - 55 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
55
- | EfficientFormer | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.681 ms | 1 - 42 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
56
- | EfficientFormer | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 0.802 ms | 1 - 39 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
57
- | EfficientFormer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.83 ms | 109 - 109 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
58
- | EfficientFormer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.62 ms | 24 - 24 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
59
- | EfficientFormer | w8a16 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | ONNX | 138.759 ms | 20 - 27 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
60
- | EfficientFormer | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 3.199 ms | 0 - 34 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
61
- | EfficientFormer | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.562 ms | 0 - 11 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
62
- | EfficientFormer | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 7.441 ms | 4 - 17 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
63
- | EfficientFormer | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.939 ms | 0 - 35 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
64
- | EfficientFormer | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 52.238 ms | 18 - 25 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
65
- | EfficientFormer | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.081 ms | 0 - 46 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
66
- | EfficientFormer | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.917 ms | 5 - 47 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
67
- | EfficientFormer | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.704 ms | 0 - 40 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
68
- | EfficientFormer | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.743 ms | 5 - 39 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
69
- | EfficientFormer | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 1.684 ms | 0 - 44 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
70
- | EfficientFormer | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 60.17 ms | 22 - 38 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
71
- | EfficientFormer | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.599 ms | 0 - 42 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
72
- | EfficientFormer | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 4.332 ms | 5 - 39 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
73
- | EfficientFormer | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.801 ms | 43 - 43 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
74
- | EfficientFormer | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.332 ms | 10 - 10 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
 
 
75
 
76
 
77
 
@@ -248,7 +251,6 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
248
  ## License
249
  * The license for the original implementation of EfficientFormer can be found
250
  [here](https://github.com/snap-research/EfficientFormer?tab=License-1-ov-file#readme).
251
- * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
252
 
253
 
254
 
 
2
  library_name: pytorch
3
  license: other
4
  tags:
5
+ - bu_auto
6
  - android
7
  pipeline_tag: image-classification
8
 
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | EfficientFormer | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 4.875 ms | 0 - 154 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
41
+ | EfficientFormer | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.001 ms | 1 - 139 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
42
+ | EfficientFormer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.48 ms | 0 - 197 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
43
+ | EfficientFormer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.616 ms | 1 - 182 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
44
+ | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.436 ms | 0 - 3 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
45
+ | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.586 ms | 1 - 2 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
46
+ | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 1.639 ms | 0 - 30 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
47
+ | EfficientFormer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2.099 ms | 0 - 155 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
48
+ | EfficientFormer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.209 ms | 1 - 139 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
49
+ | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.029 ms | 0 - 195 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
50
+ | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.102 ms | 1 - 179 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
51
+ | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.1 ms | 0 - 153 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
52
+ | EfficientFormer | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.769 ms | 0 - 155 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
53
+ | EfficientFormer | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.824 ms | 1 - 144 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
54
+ | EfficientFormer | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 0.921 ms | 0 - 114 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
55
+ | EfficientFormer | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 0.686 ms | 0 - 154 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
56
+ | EfficientFormer | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.7 ms | 1 - 141 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
57
+ | EfficientFormer | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 0.801 ms | 1 - 115 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
58
+ | EfficientFormer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.812 ms | 1 - 1 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
59
+ | EfficientFormer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.621 ms | 25 - 25 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
60
+ | EfficientFormer | w8a16 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | QNN_DLC | 7.023 ms | 0 - 152 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
61
+ | EfficientFormer | w8a16 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | ONNX | 64.274 ms | 22 - 36 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
62
+ | EfficientFormer | w8a16 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | ONNX | 139.848 ms | 20 - 26 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
63
+ | EfficientFormer | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 3.254 ms | 1 - 144 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
64
+ | EfficientFormer | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.553 ms | 0 - 2 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
65
+ | EfficientFormer | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.467 ms | 0 - 13 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
66
+ | EfficientFormer | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 1.938 ms | 0 - 145 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
67
+ | EfficientFormer | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 53.825 ms | 18 - 24 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
68
+ | EfficientFormer | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.071 ms | 0 - 170 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
69
+ | EfficientFormer | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.267 ms | 5 - 151 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
70
+ | EfficientFormer | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 0.709 ms | 0 - 148 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
71
+ | EfficientFormer | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 7.508 ms | 5 - 124 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
72
+ | EfficientFormer | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 1.694 ms | 0 - 153 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
73
+ | EfficientFormer | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 60.448 ms | 22 - 39 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
74
+ | EfficientFormer | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 0.599 ms | 0 - 147 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
75
+ | EfficientFormer | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 4.264 ms | 5 - 124 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
76
+ | EfficientFormer | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.795 ms | 0 - 0 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.dlc) |
77
+ | EfficientFormer | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.424 ms | 10 - 10 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a16.onnx.zip) |
78
 
79
 
80
 
 
251
  ## License
252
  * The license for the original implementation of EfficientFormer can be found
253
  [here](https://github.com/snap-research/EfficientFormer?tab=License-1-ov-file#readme).
 
254
 
255
 
256