v0.40.0
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.40.0 for changelog.
- README.md +47 -51
- Swin-Base_float.dlc +2 -2
- Swin-Base_float.onnx.zip +2 -2
- Swin-Base_w8a16.dlc +2 -2
- Swin-Base_w8a16.onnx.zip +2 -2
- tool-versions.yaml +1 -1
README.md
CHANGED
|
@@ -37,57 +37,53 @@ More details on model performance across various devices, can be found
|
|
| 37 |
|
| 38 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 39 |
|---|---|---|---|---|---|---|---|---|
|
| 40 |
-
| Swin-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE |
|
| 41 |
-
| Swin-Base | float |
|
| 42 |
-
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) |
|
| 43 |
-
| Swin-Base | float |
|
| 44 |
-
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) |
|
| 45 |
-
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) |
|
| 46 |
-
| Swin-Base | float |
|
| 47 |
-
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) |
|
| 48 |
-
| Swin-Base | float |
|
| 49 |
-
| Swin-Base | float |
|
| 50 |
-
| Swin-Base | float |
|
| 51 |
-
| Swin-Base | float |
|
| 52 |
-
| Swin-Base | float |
|
| 53 |
-
| Swin-Base | float |
|
| 54 |
-
| Swin-Base | float |
|
| 55 |
-
| Swin-Base | float |
|
| 56 |
-
| Swin-Base | float |
|
| 57 |
-
| Swin-Base | float |
|
| 58 |
-
| Swin-Base | float |
|
| 59 |
-
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile |
|
| 60 |
-
| Swin-Base | float | Samsung Galaxy
|
| 61 |
-
| Swin-Base | float | Samsung Galaxy
|
| 62 |
-
| Swin-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile |
|
| 63 |
-
| Swin-Base | float |
|
| 64 |
-
| Swin-Base | float |
|
| 65 |
-
| Swin-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile |
|
| 66 |
-
| Swin-Base | float | Snapdragon
|
| 67 |
-
| Swin-Base | float | Snapdragon
|
| 68 |
-
| Swin-Base |
|
| 69 |
-
| Swin-Base |
|
| 70 |
-
| Swin-Base | w8a16 |
|
| 71 |
-
| Swin-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) |
|
| 72 |
-
| Swin-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC |
|
| 73 |
-
| Swin-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) |
|
| 74 |
-
| Swin-Base | w8a16 |
|
| 75 |
-
| Swin-Base | w8a16 |
|
| 76 |
-
| Swin-Base | w8a16 |
|
| 77 |
-
| Swin-Base | w8a16 |
|
| 78 |
-
| Swin-Base | w8a16 |
|
| 79 |
-
| Swin-Base | w8a16 |
|
| 80 |
-
| Swin-Base | w8a16 |
|
| 81 |
-
| Swin-Base | w8a16 | Samsung Galaxy
|
| 82 |
-
| Swin-Base | w8a16 |
|
| 83 |
-
| Swin-Base | w8a16 |
|
| 84 |
-
| Swin-Base | w8a16 |
|
| 85 |
-
| Swin-Base | w8a16 | Snapdragon
|
| 86 |
-
| Swin-Base | w8a16 | Snapdragon
|
| 87 |
-
| Swin-Base | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 7.51 ms | 0 - 250 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 88 |
-
| Swin-Base | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 113.872 ms | 631 - 969 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 89 |
-
| Swin-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 19.46 ms | 350 - 350 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 90 |
-
| Swin-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 146.002 ms | 988 - 988 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 91 |
|
| 92 |
|
| 93 |
|
|
|
|
| 37 |
|
| 38 |
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|
| 39 |
|---|---|---|---|---|---|---|---|---|
|
| 40 |
+
| Swin-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 61.017 ms | 0 - 356 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 41 |
+
| Swin-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 55.331 ms | 1 - 314 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 42 |
+
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 28.274 ms | 0 - 350 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 43 |
+
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 29.627 ms | 1 - 336 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 44 |
+
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 21.67 ms | 0 - 33 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 45 |
+
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 19.633 ms | 0 - 57 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 46 |
+
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 19.133 ms | 0 - 62 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx.zip) |
|
| 47 |
+
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 25.077 ms | 0 - 355 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 48 |
+
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 22.649 ms | 0 - 315 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 49 |
+
| Swin-Base | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 61.017 ms | 0 - 356 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 50 |
+
| Swin-Base | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 55.331 ms | 1 - 314 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 51 |
+
| Swin-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 21.677 ms | 0 - 41 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 52 |
+
| Swin-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 19.703 ms | 0 - 66 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 53 |
+
| Swin-Base | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 31.906 ms | 0 - 347 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 54 |
+
| Swin-Base | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 29.853 ms | 36 - 342 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 55 |
+
| Swin-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 21.816 ms | 0 - 33 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 56 |
+
| Swin-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 19.575 ms | 0 - 70 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 57 |
+
| Swin-Base | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 25.077 ms | 0 - 355 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 58 |
+
| Swin-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 22.649 ms | 0 - 315 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 59 |
+
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 15.037 ms | 0 - 354 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 60 |
+
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 13.498 ms | 1 - 346 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 61 |
+
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 12.924 ms | 1 - 343 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx.zip) |
|
| 62 |
+
| Swin-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 11.895 ms | 0 - 355 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 63 |
+
| Swin-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 10.218 ms | 1 - 313 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 64 |
+
| Swin-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 9.635 ms | 1 - 314 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx.zip) |
|
| 65 |
+
| Swin-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 10.164 ms | 0 - 348 MB | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
|
| 66 |
+
| Swin-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 8.144 ms | 1 - 328 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 67 |
+
| Swin-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 8.104 ms | 1 - 328 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx.zip) |
|
| 68 |
+
| Swin-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 20.172 ms | 1019 - 1019 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.dlc) |
|
| 69 |
+
| Swin-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.541 ms | 175 - 175 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx.zip) |
|
| 70 |
+
| Swin-Base | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 39.535 ms | 0 - 277 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 71 |
+
| Swin-Base | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 20.837 ms | 0 - 85 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 72 |
+
| Swin-Base | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 20.981 ms | 0 - 279 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 73 |
+
| Swin-Base | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 552.304 ms | 142 - 170 MB | CPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 74 |
+
| Swin-Base | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 620.883 ms | 140 - 156 MB | CPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 75 |
+
| Swin-Base | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 39.535 ms | 0 - 277 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 76 |
+
| Swin-Base | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 20.942 ms | 0 - 87 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 77 |
+
| Swin-Base | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 20.715 ms | 0 - 84 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 78 |
+
| Swin-Base | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 20.981 ms | 0 - 279 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 79 |
+
| Swin-Base | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 13.827 ms | 0 - 283 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 80 |
+
| Swin-Base | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 10.808 ms | 0 - 266 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 81 |
+
| Swin-Base | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 210.961 ms | 93 - 166 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 82 |
+
| Swin-Base | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | QNN_DLC | 25.019 ms | 0 - 615 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 83 |
+
| Swin-Base | w8a16 | Snapdragon 7 Gen 5 QRD | Snapdragon® 7 Gen 5 Mobile | ONNX | 598.654 ms | 122 - 144 MB | CPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 84 |
+
| Swin-Base | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 8.134 ms | 0 - 273 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 85 |
+
| Swin-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 21.72 ms | 404 - 404 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 86 |
+
| Swin-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 186.699 ms | 133 - 133 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
|
| 88 |
|
| 89 |
|
Swin-Base_float.dlc
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a04ddaad71b81e4b7f05f6d0adbc20dde9dc3451c430c36b608900a0f0273ce
|
| 3 |
+
size 356148212
|
Swin-Base_float.onnx.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0be41b37ff37d768940b39c5f569562bf9912a77321a56f50a88117406c3656
|
| 3 |
+
size 326769810
|
Swin-Base_w8a16.dlc
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91b61a4688cc78239c29f95d20ab6fbf8424475fde1b1dc676d5beb07fbbeb1d
|
| 3 |
+
size 94599332
|
Swin-Base_w8a16.onnx.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43d40c42dd747efc0082d5b82348d8a03b0225edf8ccd73254f963415aba34dc
|
| 3 |
+
size 307813684
|
tool-versions.yaml
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
tool_versions:
|
| 2 |
onnx:
|
| 3 |
qairt: 2.37.1.250807093845_124904
|
| 4 |
-
onnx_runtime: 1.
|
|
|
|
| 1 |
tool_versions:
|
| 2 |
onnx:
|
| 3 |
qairt: 2.37.1.250807093845_124904
|
| 4 |
+
onnx_runtime: 1.23.0
|