Hugging Face's logo

qualcomm
/
EfficientFormer

Image Classification
PyTorch
LiteRT
bu_auto
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
ebd5f77
·
verified ·
1 Parent(s): b591d5d

v0.38.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

Files changed (9) hide show
  1. EfficientFormer_float.dlc +2 -2
  2. EfficientFormer_float.onnx.zip +2 -2
  3. EfficientFormer_w8a8.onnx.zip +2 -2
  4. EfficientFormer_w8a8.tflite +1 -1
  5. README.md +32 -37
  6. precompiled/qualcomm-snapdragon-x-elite/EfficientFormer_float.bin +0 -3
  7. precompiled/qualcomm-snapdragon-x-elite/EfficientFormer_float.onnx.zip +0 -3
  8. precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml +0 -3
  9. tool-versions.yaml +2 -2
EfficientFormer_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94334ddf4b23f944793f8ed8bb07fbb471f341b82a393a30c87e81ca1c967083
3
- size 49272548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7137f266a7853a857e985067132300dbcce8df973a24a69a3a82ac8b529c725a
3
+ size 49272636
EfficientFormer_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc0ed457f87da587581cebade7fac7f38a5d64ef23798a079f20bfd63c37478a
3
- size 45831683
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd3c2a2539f6da8188ec9185b21e22a32451ba40d929bf763c2dd66009c8a228
3
+ size 45831791
EfficientFormer_w8a8.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:649ca367c2ef4e384f021bb7673fde5f6ac63c338f7c78a1bbdcc30d1de24024
3
- size 27911085
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f45742fd85c426bb8071aa43cbee84e62f78d1821a26b36a5c1eb0a024c0965
3
+ size 27902653
EfficientFormer_w8a8.tflite CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c19933dacb069910915e4171f199ecd43e9162ac0cb1c308a8a9836b054fb3ed
3
  size 12793736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4684310be3d79f41cbabb0944dc6a619e017f5fb9c59621e4a7d3a9f37ac3e18
3
  size 12793736
README.md CHANGED
@@ -36,42 +36,37 @@ 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 | 4.93 ms | 0 - 48 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
40
- | EfficientFormer | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.007 ms | 1 - 34 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
41
- | EfficientFormer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 3.825 ms | 0 - 55 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
42
- | EfficientFormer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.767 ms | 0 - 45 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
43
- | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.519 ms | 0 - 157 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
44
- | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.646 ms | 1 - 10 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
45
- | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 5.951 ms | 0 - 67 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
46
- | EfficientFormer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2.096 ms | 0 - 48 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
47
- | EfficientFormer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.294 ms | 1 - 34 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
48
- | EfficientFormer | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1.523 ms | 0 - 156 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
49
- | EfficientFormer | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 1.625 ms | 0 - 13 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
50
- | EfficientFormer | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 6.125 ms | 0 - 39 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
51
- | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.057 ms | 0 - 59 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
52
- | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.122 ms | 0 - 41 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
53
- | EfficientFormer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.099 ms | 0 - 47 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
54
- | EfficientFormer | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.941 ms | 0 - 52 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
55
- | EfficientFormer | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.975 ms | 1 - 39 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
56
- | EfficientFormer | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.722 ms | 1 - 42 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 | 1.887 ms | 105 - 105 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
58
- | EfficientFormer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.176 ms | 26 - 26 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
59
- | EfficientFormer | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 1.679 ms | 0 - 26 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
60
- | EfficientFormer | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.844 ms | 0 - 44 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
61
- | EfficientFormer | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.745 ms | 0 - 59 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
62
- | EfficientFormer | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.817 ms | 23 - 50 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
63
- | EfficientFormer | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 1.0 ms | 0 - 27 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
64
- | EfficientFormer | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 4.468 ms | 0 - 37 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
65
- | EfficientFormer | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 34.985 ms | 14 - 29 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
66
- | EfficientFormer | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 40.829 ms | 1 - 82 MB | GPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
67
- | EfficientFormer | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 31.87 ms | 13 - 22 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
68
- | EfficientFormer | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.746 ms | 0 - 60 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
69
- | EfficientFormer | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 8.049 ms | 21 - 49 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
70
- | EfficientFormer | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.522 ms | 0 - 43 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
71
- | EfficientFormer | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.706 ms | 27 - 80 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
72
- | EfficientFormer | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.495 ms | 1 - 30 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
73
- | EfficientFormer | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 4.977 ms | 0 - 40 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
74
- | EfficientFormer | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.084 ms | 25 - 25 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
75
 
76
 
77
 
@@ -153,7 +148,7 @@ from qai_hub_models.models.efficientformer import Model
153
  torch_model = Model.from_pretrained()
154
 
155
  # Device
156
- device = hub.Device("Samsung Galaxy S24")
157
 
158
  # Trace model
159
  input_shape = torch_model.get_input_spec()
 
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 | 4.918 ms | 0 - 48 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
40
+ | EfficientFormer | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 5.024 ms | 1 - 34 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
41
+ | EfficientFormer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 3.826 ms | 0 - 56 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
42
+ | EfficientFormer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.662 ms | 0 - 43 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
43
+ | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.528 ms | 0 - 157 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
44
+ | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 1.63 ms | 0 - 11 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
45
+ | EfficientFormer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 5.185 ms | 1 - 13 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
46
+ | EfficientFormer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2.096 ms | 0 - 49 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.tflite) |
47
+ | EfficientFormer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.304 ms | 1 - 33 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 - 61 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 | 1.113 ms | 1 - 42 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 | 3.603 ms | 0 - 46 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 | 0.814 ms | 0 - 54 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 | 0.832 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 | 2.616 ms | 0 - 44 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
54
+ | EfficientFormer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 1.923 ms | 103 - 103 MB | NPU | [EfficientFormer.dlc](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.dlc) |
55
+ | EfficientFormer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.397 ms | 25 - 25 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer.onnx.zip) |
56
+ | EfficientFormer | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 1.666 ms | 0 - 27 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
57
+ | EfficientFormer | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 0.843 ms | 0 - 51 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
58
+ | EfficientFormer | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 0.741 ms | 0 - 59 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
59
+ | EfficientFormer | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 7.688 ms | 21 - 48 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
60
+ | EfficientFormer | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 0.992 ms | 0 - 27 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
61
+ | EfficientFormer | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 4.166 ms | 0 - 37 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
62
+ | EfficientFormer | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 35.184 ms | 12 - 27 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
63
+ | EfficientFormer | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 31.712 ms | 0 - 75 MB | GPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
64
+ | EfficientFormer | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 30.835 ms | 13 - 23 MB | CPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
65
+ | EfficientFormer | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.52 ms | 0 - 42 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
66
+ | EfficientFormer | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.36 ms | 25 - 86 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
67
+ | EfficientFormer | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 0.41 ms | 0 - 30 MB | NPU | [EfficientFormer.tflite](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.tflite) |
68
+ | EfficientFormer | w8a8 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.366 ms | 0 - 44 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
69
+ | EfficientFormer | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.483 ms | 25 - 25 MB | NPU | [EfficientFormer.onnx.zip](https://huggingface.co/qualcomm/EfficientFormer/blob/main/EfficientFormer_w8a8.onnx.zip) |
 
 
 
 
 
70
 
71
 
72
 
 
148
  torch_model = Model.from_pretrained()
149
 
150
  # Device
151
+ device = hub.Device("Samsung Galaxy S25")
152
 
153
  # Trace model
154
  input_shape = torch_model.get_input_spec()
precompiled/qualcomm-snapdragon-x-elite/EfficientFormer_float.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:670bb656fb43b2684d8fe8e26d45f5f33c6746abed7c0ad147531286ae3efbc4
3
- size 26038272
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/EfficientFormer_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:82f78e9953785ba22308adfb26a7f0eeb4b1ba9419198ab66521a1aa643bb078
3
- size 23138215
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml DELETED
@@ -1,3 +0,0 @@
1
- tool_versions:
2
- precompiled_qnn_onnx:
3
- qairt: 2.36.4.250725200057_123280
 
 
 
 
tool-versions.yaml CHANGED
@@ -1,4 +1,4 @@
1
  tool_versions:
2
  onnx:
3
- qairt: 2.36.4.250725200057_123280
4
- onnx_runtime: 1.22.0
 
1
  tool_versions:
2
  onnx:
3
+ qairt: 2.37.1.250807093845_124904
4
+ onnx_runtime: 1.22.2