qaihm-bot commited on
Commit
97ea8aa
·
verified ·
1 Parent(s): 67043ee

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

MobileSam_MobileSAMDecoder_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c83d00537a4c71ba90b5b87e905101c1ba22e910cf61382ae7ec7083decfb423
3
- size 25510740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad19f40e6bad96315c1ccf47043e92c5f52fd49bf4cd2b69572e266b8364dbe6
3
+ size 25510844
MobileSam_MobileSAMDecoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:572b565c3f1789a75f576af59de884d2fa46350e2617d3f7dc7ee34615584f69
3
- size 19071937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7301f2424305a42f265488a2d7b891a31d782bd242374b1b485cd4332a1bd0f9
3
+ size 19071944
MobileSam_MobileSAMDecoder_float.tflite CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:491c4a06668b2bb383bdbf2893ae8089ae56e51861d36df43e89bb647244780b
3
- size 24802464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6493fd00d20d2ec703b9cf6ec5ae288b4562a608cf5570caf3f8df9c8c4451
3
+ size 24802456
MobileSam_MobileSAMEncoder_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c05f339c6d60c3f2089da1611998c80716e728f4d6fa7d22236548bea8c11b1c
3
- size 28170860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9837e8d3dc23c6afe77b8f294e5ce9d467dad24f3c9d34ce7cc267d719287c
3
+ size 28170956
MobileSam_MobileSAMEncoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb9cca334e7937df6e447750723e0a64b2c24f4b43af95c91c2e2a2ed643235c
3
- size 21650114
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e735d01b29e96274483bb5c256a24a13afe5ca15c88b06f63f8a30a10505b20b
3
+ size 21650122
MobileSam_MobileSAMEncoder_float.tflite CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a137da0b7a283e84a3a1814d7580d58482c97b9ea10f90ab60c7865eaf77aa3a
3
- size 27921296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84ed014f0d90aac294d7e0c871bcb4b49d62c06c9ed08ef216a4dfae6d31867
3
+ size 27921280
README.md CHANGED
@@ -38,64 +38,54 @@ 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
- | MobileSAMEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 324.864 ms | 0 - 529 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
42
- | MobileSAMEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 260.424 ms | 0 - 528 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
43
- | MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 514.336 ms | 0 - 1846 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
44
- | MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 552.762 ms | 12 - 1872 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
45
- | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 196.222 ms | 4 - 86 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
46
- | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 155.047 ms | 12 - 81 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
47
- | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 339.53 ms | 96 - 161 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
48
- | MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 198.65 ms | 4 - 533 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
49
- | MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 160.433 ms | 3 - 1080 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
50
- | MobileSAMEncoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 324.864 ms | 0 - 529 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
51
- | MobileSAMEncoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 260.424 ms | 0 - 528 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
52
- | MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 197.144 ms | 4 - 84 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
53
- | MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 156.008 ms | 12 - 83 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
54
- | MobileSAMEncoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 558.486 ms | 1 - 1116 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
55
- | MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 196.223 ms | 4 - 88 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
56
- | MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 155.286 ms | 9 - 76 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
57
- | MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 198.65 ms | 4 - 533 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
58
- | MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 160.433 ms | 3 - 1080 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
59
- | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 138.04 ms | 0 - 525 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
60
- | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 111.694 ms | 12 - 536 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
61
- | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 255.0 ms | 127 - 262 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
62
- | MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 110.676 ms | 4 - 532 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
63
- | MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 91.237 ms | 12 - 508 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
64
- | MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 185.566 ms | 116 - 457 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
65
- | MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 93.109 ms | 0 - 521 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
66
- | MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 73.307 ms | 12 - 1071 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
67
- | MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 155.196 ms | 126 - 360 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
68
- | MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 150.151 ms | 954 - 954 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
69
- | MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 344.225 ms | 132 - 132 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
70
- | MobileSAMDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.769 ms | 0 - 48 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
71
- | MobileSAMDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.294 ms | 4 - 140 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
72
- | MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.45 ms | 0 - 53 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
73
- | MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 11.466 ms | 4 - 73 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
74
- | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 6.301 ms | 0 - 31 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
75
- | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.053 ms | 4 - 26 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
76
- | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.043 ms | 0 - 51 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
77
- | MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 7.447 ms | 0 - 51 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
78
- | MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.089 ms | 2 - 139 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
79
- | MobileSAMDecoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 14.769 ms | 0 - 48 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
80
- | MobileSAMDecoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 12.294 ms | 4 - 140 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
81
- | MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 6.303 ms | 0 - 30 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
82
- | MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 5.071 ms | 4 - 29 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
83
- | MobileSAMDecoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.828 ms | 0 - 51 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
84
- | MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 6.311 ms | 0 - 31 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
85
- | MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 5.091 ms | 4 - 33 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
86
- | MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 7.447 ms | 0 - 51 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
87
- | MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 6.089 ms | 2 - 139 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
88
- | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.424 ms | 0 - 55 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
89
- | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.536 ms | 5 - 154 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
90
- | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.48 ms | 4 - 84 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
91
- | MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 3.469 ms | 0 - 54 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
92
- | MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.635 ms | 4 - 135 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
93
- | MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.102 ms | 1 - 74 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
94
- | MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 3.158 ms | 0 - 50 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
95
- | MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 2.334 ms | 4 - 57 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
96
- | MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 3.386 ms | 4 - 84 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
97
- | MobileSAMDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 5.517 ms | 64 - 64 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
98
- | MobileSAMDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.453 ms | 11 - 11 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
99
 
100
 
101
 
@@ -110,9 +100,9 @@ pip install "qai-hub-models[mobilesam]" git+https://github.com/ChaoningZhang/Mob
110
  ```
111
 
112
 
113
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
114
 
115
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
116
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
117
 
118
  With this API token, you can configure your client to run models on the cloud
@@ -120,7 +110,7 @@ hosted devices.
120
  ```bash
121
  qai-hub configure --api_token API_TOKEN
122
  ```
123
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
124
 
125
 
126
 
@@ -231,7 +221,7 @@ With the output of the model, you can compute like PSNR, relative errors or
231
  spot check the output with expected output.
232
 
233
  **Note**: This on-device profiling and inference requires access to Qualcomm®
234
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
235
 
236
 
237
 
 
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
+ | MobileSAMEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 323.32 ms | 4 - 536 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
42
+ | MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 519.019 ms | 0 - 1845 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
43
+ | MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 460.861 ms | 12 - 776 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
44
+ | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 194.834 ms | 4 - 82 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
45
+ | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 151.163 ms | 12 - 105 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
46
+ | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 343.314 ms | 118 - 143 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
47
+ | MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 198.285 ms | 4 - 534 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
48
+ | MobileSAMEncoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 323.32 ms | 4 - 536 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
49
+ | MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 151.446 ms | 15 - 107 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
50
+ | MobileSAMEncoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 557.47 ms | 4 - 1121 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
51
+ | MobileSAMEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 453.8 ms | 2 - 594 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
52
+ | MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 153.239 ms | 12 - 102 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
53
+ | MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 198.285 ms | 4 - 534 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
54
+ | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 139.876 ms | 0 - 523 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
55
+ | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 106.741 ms | 12 - 1653 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
56
+ | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 254.414 ms | 126 - 255 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
57
+ | MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 107.657 ms | 3 - 529 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
58
+ | MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 81.528 ms | 0 - 1016 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
59
+ | MobileSAMEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 186.033 ms | 116 - 460 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
60
+ | MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 98.649 ms | 0 - 521 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
61
+ | MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 72.868 ms | 12 - 1073 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
62
+ | MobileSAMEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 88.506 ms | 101 - 465 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
63
+ | MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 148.428 ms | 490 - 490 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
64
+ | MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 359.459 ms | 132 - 132 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
65
+ | MobileSAMDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 14.239 ms | 0 - 46 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
66
+ | MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.071 ms | 0 - 56 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
67
+ | MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 8.692 ms | 4 - 59 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
68
+ | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 6.0 ms | 0 - 33 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
69
+ | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.716 ms | 4 - 21 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
70
+ | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.424 ms | 0 - 48 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
71
+ | MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 7.148 ms | 0 - 46 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
72
+ | MobileSAMDecoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 14.239 ms | 0 - 46 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
73
+ | MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.732 ms | 4 - 21 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
74
+ | MobileSAMDecoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.377 ms | 0 - 51 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
75
+ | MobileSAMDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 7.249 ms | 2 - 80 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
76
+ | MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.736 ms | 4 - 21 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
77
+ | MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 7.148 ms | 0 - 46 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
78
+ | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.197 ms | 0 - 58 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
79
+ | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.29 ms | 4 - 74 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
80
+ | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.741 ms | 3 - 85 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
81
+ | MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 3.409 ms | 0 - 51 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
82
+ | MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.653 ms | 0 - 58 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
83
+ | MobileSAMDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.232 ms | 3 - 77 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
84
+ | MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 3.342 ms | 0 - 49 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
85
+ | MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_DLC | 2.166 ms | 4 - 53 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
86
+ | MobileSAMDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 3.513 ms | 4 - 85 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
87
+ | MobileSAMDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 5.165 ms | 20 - 20 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
88
+ | MobileSAMDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.735 ms | 11 - 11 MB | NPU | [MobileSam.onnx.zip](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx.zip) |
 
 
 
 
 
 
 
 
 
 
89
 
90
 
91
 
 
100
  ```
101
 
102
 
103
+ ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
104
 
105
+ Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
106
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
107
 
108
  With this API token, you can configure your client to run models on the cloud
 
110
  ```bash
111
  qai-hub configure --api_token API_TOKEN
112
  ```
113
+ Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
114
 
115
 
116
 
 
221
  spot check the output with expected output.
222
 
223
  **Note**: This on-device profiling and inference requires access to Qualcomm®
224
+ AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
225
 
226
 
227