qaihm-bot commited on
Commit
b221815
·
verified ·
1 Parent(s): 6403b35

See https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.

README.md CHANGED
@@ -24,6 +24,7 @@ More details on model performance across various devices, can be found
24
  [here](https://aihub.qualcomm.com/models/mobilesam).
25
 
26
 
 
27
  ### Model Details
28
 
29
  - **Model Type:** Model_use_case.semantic_segmentation
@@ -37,56 +38,54 @@ 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
- | MobileSAMEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 744.282 ms | 33 - 379 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
41
- | MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 592.073 ms | 33 - 729 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
42
  | MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 490.954 ms | 12 - 618 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
43
- | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 438.155 ms | 33 - 62 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
44
  | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 271.374 ms | 12 - 86 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
45
- | MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 424.391 ms | 33 - 376 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
46
  | MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 277.597 ms | 1 - 1161 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
47
- | MobileSAMEncoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 744.282 ms | 33 - 379 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
48
- | MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 425.325 ms | 33 - 56 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
49
  | MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 273.237 ms | 12 - 85 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
50
- | MobileSAMEncoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 584.827 ms | 31 - 378 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
51
  | MobileSAMEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 436.56 ms | 3 - 650 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
52
- | MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 438.208 ms | 26 - 58 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
53
  | MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 275.045 ms | 12 - 87 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
54
- | MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 424.391 ms | 33 - 376 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
55
  | MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 277.597 ms | 1 - 1161 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
56
- | MobileSAMEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 460.958 ms | 33 - 58 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
57
  | MobileSAMEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 271.764 ms | 12 - 73 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
58
  | MobileSAMEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 413.682 ms | 80 - 174 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
59
- | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 348.17 ms | 33 - 721 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 | 205.547 ms | 12 - 2423 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 | 312.791 ms | 110 - 832 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
62
- | MobileSAMEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 273.427 ms | 33 - 379 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
63
  | MobileSAMEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 173.722 ms | 8 - 1176 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
64
  | MobileSAMEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 266.959 ms | 128 - 531 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
65
  | MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 297.893 ms | 48 - 48 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
66
  | MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 466.886 ms | 130 - 130 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
67
- | MobileSAMDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 16.575 ms | 0 - 54 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
68
- | MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.251 ms | 0 - 57 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
69
  | MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 8.386 ms | 4 - 54 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
70
- | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.302 ms | 0 - 29 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
71
  | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 6.097 ms | 4 - 21 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
72
- | MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 8.429 ms | 0 - 55 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
73
  | MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 7.328 ms | 0 - 45 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
74
- | MobileSAMDecoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 16.575 ms | 0 - 54 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
75
- | MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 7.262 ms | 0 - 28 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
76
  | MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 6.112 ms | 4 - 19 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
77
- | MobileSAMDecoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.685 ms | 0 - 50 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
78
  | MobileSAMDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 7.457 ms | 1 - 62 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
79
- | MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 7.272 ms | 0 - 32 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
80
  | MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 6.109 ms | 4 - 24 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
81
- | MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 8.429 ms | 0 - 55 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
82
  | MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 7.328 ms | 0 - 45 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
83
- | MobileSAMDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.312 ms | 0 - 29 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
84
  | MobileSAMDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 6.103 ms | 3 - 27 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
85
  | MobileSAMDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 9.413 ms | 0 - 47 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
86
- | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.054 ms | 0 - 62 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
87
  | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.198 ms | 4 - 59 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
88
  | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.161 ms | 4 - 72 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
89
- | MobileSAMDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 5.065 ms | 0 - 58 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
90
  | MobileSAMDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.093 ms | 4 - 54 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
91
  | MobileSAMDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.454 ms | 1 - 60 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
92
  | MobileSAMDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.001 ms | 12 - 12 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
@@ -148,26 +147,7 @@ device. This script does the following:
148
  ```bash
149
  python -m qai_hub_models.models.mobilesam.export
150
  ```
151
- ```
152
- Profiling Results
153
- ------------------------------------------------------------
154
- MobileSAMEncoder
155
- Device : cs_8275 (ANDROID 14)
156
- Runtime : TFLITE
157
- Estimated inference time (ms) : 744.3
158
- Estimated peak memory usage (MB): [33, 379]
159
- Total # Ops : 592
160
- Compute Unit(s) : npu (532 ops) gpu (0 ops) cpu (60 ops)
161
-
162
- ------------------------------------------------------------
163
- MobileSAMDecoder
164
- Device : cs_8275 (ANDROID 14)
165
- Runtime : TFLITE
166
- Estimated inference time (ms) : 16.6
167
- Estimated peak memory usage (MB): [0, 54]
168
- Total # Ops : 846
169
- Compute Unit(s) : npu (846 ops) gpu (0 ops) cpu (0 ops)
170
- ```
171
 
172
 
173
  ## How does this work?
 
24
  [here](https://aihub.qualcomm.com/models/mobilesam).
25
 
26
 
27
+
28
  ### Model Details
29
 
30
  - **Model Type:** Model_use_case.semantic_segmentation
 
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 | 741.976 ms | 33 - 379 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
42
+ | MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 573.806 ms | 33 - 727 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
43
  | MobileSAMEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 490.954 ms | 12 - 618 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
44
+ | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 428.807 ms | 33 - 61 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
45
  | MobileSAMEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 271.374 ms | 12 - 86 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
46
+ | MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 423.867 ms | 33 - 379 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
47
  | MobileSAMEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 277.597 ms | 1 - 1161 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
48
+ | MobileSAMEncoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 741.976 ms | 33 - 379 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
49
+ | MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 436.727 ms | 33 - 58 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
50
  | MobileSAMEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 273.237 ms | 12 - 85 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
51
+ | MobileSAMEncoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 585.302 ms | 33 - 380 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
52
  | MobileSAMEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 436.56 ms | 3 - 650 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
53
+ | MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 437.207 ms | 33 - 56 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
54
  | MobileSAMEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 275.045 ms | 12 - 87 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
55
+ | MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 423.867 ms | 33 - 379 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
56
  | MobileSAMEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 277.597 ms | 1 - 1161 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
57
+ | MobileSAMEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 444.556 ms | 33 - 59 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
58
  | MobileSAMEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 271.764 ms | 12 - 73 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
59
  | MobileSAMEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 413.682 ms | 80 - 174 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
60
+ | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 339.333 ms | 33 - 720 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
61
  | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 205.547 ms | 12 - 2423 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
62
  | MobileSAMEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 312.791 ms | 110 - 832 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
 
63
  | MobileSAMEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 173.722 ms | 8 - 1176 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
64
  | MobileSAMEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 266.959 ms | 128 - 531 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
65
  | MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 297.893 ms | 48 - 48 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
66
  | MobileSAMEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 466.886 ms | 130 - 130 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
67
+ | MobileSAMDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 52.956 ms | 0 - 54 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
68
+ | MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.277 ms | 0 - 57 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
69
  | MobileSAMDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 8.386 ms | 4 - 54 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
70
+ | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.234 ms | 0 - 28 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
71
  | MobileSAMDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 6.097 ms | 4 - 21 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
72
+ | MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 8.42 ms | 0 - 54 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
73
  | MobileSAMDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 7.328 ms | 0 - 45 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
74
+ | MobileSAMDecoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 52.956 ms | 0 - 54 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
75
+ | MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 7.27 ms | 0 - 27 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
76
  | MobileSAMDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 6.112 ms | 4 - 19 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
77
+ | MobileSAMDecoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.722 ms | 0 - 51 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
78
  | MobileSAMDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 7.457 ms | 1 - 62 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
79
+ | MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 7.278 ms | 0 - 29 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
80
  | MobileSAMDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 6.109 ms | 4 - 24 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
81
+ | MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 8.42 ms | 0 - 54 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
82
  | MobileSAMDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 7.328 ms | 0 - 45 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
83
+ | MobileSAMDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 7.27 ms | 0 - 32 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
84
  | MobileSAMDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 6.103 ms | 3 - 27 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
85
  | MobileSAMDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 9.413 ms | 0 - 47 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
86
+ | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.064 ms | 0 - 66 MB | NPU | [MobileSam.tflite](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.tflite) |
87
  | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.198 ms | 4 - 59 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
88
  | MobileSAMDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.161 ms | 4 - 72 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
 
89
  | MobileSAMDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.093 ms | 4 - 54 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
90
  | MobileSAMDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 5.454 ms | 1 - 60 MB | NPU | [MobileSam.onnx](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.onnx) |
91
  | MobileSAMDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.001 ms | 12 - 12 MB | NPU | [MobileSam.dlc](https://huggingface.co/qualcomm/MobileSam/blob/main/MobileSam.dlc) |
 
147
  ```bash
148
  python -m qai_hub_models.models.mobilesam.export
149
  ```
150
+
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
 
152
 
153
  ## How does this work?
precompiled/qualcomm-snapdragon-x-elite/MobileSam_MobileSAMDecoder.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbe99171ba438b5335d43cd877a54829c04934185b6332390ba95b659ef068ae
3
  size 12366312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f735389200b0af5a51f985d3c424305d8855cddcdf5a35edfae53238565b7b84
3
  size 12366312
precompiled/qualcomm-snapdragon-x-elite/MobileSam_MobileSAMDecoder.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f62ff611aceb7dc62809b41db06c61be355b30c833453f0e5037b60f205add79
3
- size 9739314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91433862ff6aa7a5d9e8ed892c64c0df374827e63e7b6c4b5950c66065c2b50d
3
+ size 9739248
precompiled/qualcomm-snapdragon-x-elite/MobileSam_MobileSAMEncoder.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99472d278dca38972a1766be751b002a0f887b72f3cdec82d9a20d7c242090bf
3
- size 17566396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6425de22a5ab77f462457461e769597ab8af551e52ce213a631ade733008a5
3
+ size 17566411
precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ qnn_context_binary:
3
+ qairt: 2.34.2.250528164111_119506
4
+ precompiled_qnn_onnx:
5
+ qairt: 2.33.2.250410134701_117956