v0.43.0
Browse filesSee https://github.com/quic/ai-hub-models/releases/v0.43.0 for changelog.
- README.md +35 -47
- Swin-Base_float.dlc +1 -1
- Swin-Base_float.onnx.zip +1 -1
- Swin-Base_w8a16.dlc +0 -3
- Swin-Base_w8a16.onnx.zip +2 -2
README.md
CHANGED
|
@@ -37,53 +37,41 @@ 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 | 60.
|
| 41 |
-
| Swin-Base | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 54.
|
| 42 |
-
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 28.
|
| 43 |
-
| Swin-Base | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 28.
|
| 44 |
-
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 21.
|
| 45 |
-
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 19.
|
| 46 |
-
| Swin-Base | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 19.
|
| 47 |
-
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 25.
|
| 48 |
-
| Swin-Base | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 22.
|
| 49 |
-
| Swin-Base | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 60.
|
| 50 |
-
| Swin-Base | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 54.
|
| 51 |
-
| Swin-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 21.
|
| 52 |
-
| Swin-Base | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 19.
|
| 53 |
-
| Swin-Base | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 31.
|
| 54 |
-
| Swin-Base | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 28.
|
| 55 |
-
| Swin-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 21.
|
| 56 |
-
| Swin-Base | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 19.
|
| 57 |
-
| Swin-Base | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 25.
|
| 58 |
-
| Swin-Base | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 22.
|
| 59 |
-
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE |
|
| 60 |
-
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC |
|
| 61 |
-
| Swin-Base | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 12.
|
| 62 |
-
| Swin-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 11.
|
| 63 |
-
| Swin-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 9.
|
| 64 |
-
| Swin-Base | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 9.
|
| 65 |
-
| Swin-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 9.
|
| 66 |
-
| Swin-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 8.
|
| 67 |
-
| Swin-Base | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 8.
|
| 68 |
-
| Swin-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 19.906 ms |
|
| 69 |
-
| Swin-Base | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 19.
|
| 70 |
-
| Swin-Base | w8a16 |
|
| 71 |
-
| Swin-Base | w8a16 |
|
| 72 |
-
| Swin-Base | w8a16 |
|
| 73 |
-
| Swin-Base | w8a16 |
|
| 74 |
-
| Swin-Base | w8a16 |
|
| 75 |
-
| Swin-Base | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 38.0 ms | 0 - 264 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 | 19.967 ms | 0 - 67 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 | 19.984 ms | 0 - 74 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 | 20.221 ms | 0 - 264 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 | 13.369 ms | 0 - 270 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 | 10.371 ms | 0 - 259 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 | 207.429 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 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_DLC | 23.508 ms | 0 - 321 MB | NPU | [Swin-Base.dlc](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.dlc) |
|
| 83 |
-
| Swin-Base | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 595.51 ms | 119 - 141 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 | 8.022 ms | 4 - 277 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 | 21.391 ms | 415 - 415 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 | 197.49 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 |
|
|
|
|
| 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 | 60.863 ms | 0 - 357 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 | 54.606 ms | 0 - 316 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 | 28.421 ms | 0 - 354 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 | 28.432 ms | 0 - 332 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 | 21.676 ms | 0 - 36 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 | 19.239 ms | 0 - 72 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 | 19.132 ms | 0 - 63 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 | 25.072 ms | 0 - 357 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 | 22.047 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 | 60.863 ms | 0 - 357 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 | 54.606 ms | 0 - 316 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 | 21.722 ms | 0 - 34 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 | 19.375 ms | 0 - 69 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 | 31.824 ms | 0 - 348 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 | 28.371 ms | 1 - 308 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 | 21.928 ms | 0 - 39 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 | 19.262 ms | 0 - 60 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 | 25.072 ms | 0 - 357 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 | 22.047 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 | 14.931 ms | 32 - 391 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 | 12.981 ms | 1 - 347 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 | 12.682 ms | 1 - 349 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 | 11.82 ms | 0 - 352 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 | 9.982 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 | 9.663 ms | 1 - 317 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 | 9.831 ms | 0 - 351 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 | 8.0 ms | 1 - 331 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 | 8.067 ms | 0 - 329 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 | 19.906 ms | 1036 - 1036 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 | 19.46 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 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | ONNX | 1166.756 ms | 58 - 91 MB | CPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 71 |
+
| Swin-Base | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 547.038 ms | 127 - 149 MB | CPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 72 |
+
| Swin-Base | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 204.22 ms | 87 - 159 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 73 |
+
| Swin-Base | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 599.119 ms | 113 - 137 MB | CPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
| 74 |
+
| Swin-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 201.82 ms | 133 - 133 MB | NPU | [Swin-Base.onnx.zip](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base_w8a16.onnx.zip) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
|
| 76 |
|
| 77 |
|
Swin-Base_float.dlc
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 356456956
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1954ff67cb5fdb43922375f7c0c5c5af7a4197feaeb1a05a034791304128b9ae
|
| 3 |
size 356456956
|
Swin-Base_float.onnx.zip
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 326781102
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0add922e0f35f4b59b5daaffc4ea2d01136449dd3ef0fa67fd7b2fbca3199c70
|
| 3 |
size 326781102
|
Swin-Base_w8a16.dlc
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:694fc43fc5424fd5ef7a6fc917f39efb8d98f23df10c9bf2b6a8bfb469d203e0
|
| 3 |
-
size 94754604
|
|
|
|
|
|
|
|
|
|
|
|
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:bfa80772717b2ca4fd7bde9e70e4c9434a999c814d4ff7da8aaf7e0c72514f73
|
| 3 |
+
size 307860248
|