qaihm-bot commited on
Commit
0e54b44
·
verified ·
1 Parent(s): e827348

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

Mobile-VIT_w8a16.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:634ccfc594e50915f93daa2068af66c80cf23de340db984954b5de566d3d743e
3
  size 6826313
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93edf64214bdd448f20baad2eae47ec39fa421018b8b56042cad1a7acd195e50
3
  size 6826313
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/mobile_vit).
25
 
26
 
 
27
  ### Model Details
28
 
29
  - **Model Type:** Model_use_case.image_classification
@@ -36,52 +37,52 @@ 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
- | Mobile-VIT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.171 ms | 0 - 44 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
40
  | Mobile-VIT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 11.071 ms | 1 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
41
- | Mobile-VIT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.759 ms | 0 - 51 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
42
  | Mobile-VIT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 6.473 ms | 1 - 48 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
43
- | Mobile-VIT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.771 ms | 0 - 69 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
44
  | Mobile-VIT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.305 ms | 1 - 14 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
45
- | Mobile-VIT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.599 ms | 0 - 44 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
46
  | Mobile-VIT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 5.196 ms | 1 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
47
- | Mobile-VIT | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 12.171 ms | 0 - 44 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
48
  | Mobile-VIT | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 11.071 ms | 1 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
49
- | Mobile-VIT | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.789 ms | 0 - 70 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
50
  | Mobile-VIT | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.347 ms | 0 - 13 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
51
- | Mobile-VIT | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 7.927 ms | 0 - 42 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
52
  | Mobile-VIT | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 7.361 ms | 1 - 39 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
53
- | Mobile-VIT | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.735 ms | 0 - 71 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
54
  | Mobile-VIT | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.358 ms | 4 - 17 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
55
- | Mobile-VIT | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.599 ms | 0 - 44 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
56
  | Mobile-VIT | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 5.196 ms | 1 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
57
- | Mobile-VIT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 4.753 ms | 0 - 71 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
58
  | Mobile-VIT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 4.336 ms | 1 - 13 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
59
  | Mobile-VIT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 4.653 ms | 0 - 38 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.onnx) |
60
- | Mobile-VIT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.287 ms | 0 - 58 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
61
  | Mobile-VIT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.918 ms | 0 - 60 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
62
  | Mobile-VIT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.178 ms | 0 - 59 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.onnx) |
63
- | Mobile-VIT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 3.223 ms | 0 - 47 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
64
  | Mobile-VIT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.809 ms | 1 - 53 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
65
  | Mobile-VIT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.586 ms | 0 - 50 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.onnx) |
66
  | Mobile-VIT | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.794 ms | 37 - 37 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
67
  | Mobile-VIT | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 4.979 ms | 12 - 12 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.onnx) |
68
- | Mobile-VIT | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.728 ms | 0 - 36 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
69
- | Mobile-VIT | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.247 ms | 0 - 46 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
70
- | Mobile-VIT | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.762 ms | 0 - 12 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
71
- | Mobile-VIT | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.187 ms | 0 - 37 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
72
- | Mobile-VIT | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 16.83 ms | 0 - 46 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
73
- | Mobile-VIT | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 6.728 ms | 0 - 36 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
74
- | Mobile-VIT | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 3.772 ms | 0 - 14 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
75
- | Mobile-VIT | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 4.771 ms | 0 - 37 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
76
- | Mobile-VIT | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 3.767 ms | 0 - 12 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
77
- | Mobile-VIT | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.187 ms | 0 - 37 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
78
- | Mobile-VIT | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.746 ms | 0 - 12 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
79
  | Mobile-VIT | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 13.588 ms | 14 - 76 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.onnx) |
80
- | Mobile-VIT | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.45 ms | 0 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
81
  | Mobile-VIT | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.105 ms | 19 - 161 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.onnx) |
82
- | Mobile-VIT | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.797 ms | 0 - 40 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
83
  | Mobile-VIT | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 7.002 ms | 19 - 136 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.onnx) |
84
- | Mobile-VIT | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.285 ms | 0 - 0 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
85
  | Mobile-VIT | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 13.174 ms | 29 - 29 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.onnx) |
86
 
87
 
@@ -140,17 +141,7 @@ device. This script does the following:
140
  ```bash
141
  python -m qai_hub_models.models.mobile_vit.export
142
  ```
143
- ```
144
- Profiling Results
145
- ------------------------------------------------------------
146
- Mobile-VIT
147
- Device : cs_8275 (ANDROID 14)
148
- Runtime : TFLITE
149
- Estimated inference time (ms) : 12.2
150
- Estimated peak memory usage (MB): [0, 44]
151
- Total # Ops : 577
152
- Compute Unit(s) : npu (577 ops) gpu (0 ops) cpu (0 ops)
153
- ```
154
 
155
 
156
  ## How does this work?
 
24
  [here](https://aihub.qualcomm.com/models/mobile_vit).
25
 
26
 
27
+
28
  ### Model Details
29
 
30
  - **Model Type:** Model_use_case.image_classification
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | Mobile-VIT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.119 ms | 0 - 44 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
41
  | Mobile-VIT | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 11.071 ms | 1 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
42
+ | Mobile-VIT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 6.768 ms | 0 - 49 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
43
  | Mobile-VIT | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 6.473 ms | 1 - 48 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
44
+ | Mobile-VIT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.731 ms | 0 - 70 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
45
  | Mobile-VIT | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.305 ms | 1 - 14 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
46
+ | Mobile-VIT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.64 ms | 0 - 44 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
47
  | Mobile-VIT | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 5.196 ms | 1 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
48
+ | Mobile-VIT | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 12.119 ms | 0 - 44 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
49
  | Mobile-VIT | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 11.071 ms | 1 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
50
+ | Mobile-VIT | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.777 ms | 0 - 69 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
51
  | Mobile-VIT | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.347 ms | 0 - 13 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
52
+ | Mobile-VIT | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 7.918 ms | 0 - 42 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
53
  | Mobile-VIT | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 7.361 ms | 1 - 39 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
54
+ | Mobile-VIT | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.763 ms | 0 - 68 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
55
  | Mobile-VIT | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.358 ms | 4 - 17 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
56
+ | Mobile-VIT | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.64 ms | 0 - 44 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
57
  | Mobile-VIT | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 5.196 ms | 1 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
58
+ | Mobile-VIT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 4.781 ms | 0 - 69 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
59
  | Mobile-VIT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 4.336 ms | 1 - 13 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
60
  | Mobile-VIT | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 4.653 ms | 0 - 38 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.onnx) |
61
+ | Mobile-VIT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.283 ms | 0 - 58 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
62
  | Mobile-VIT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.918 ms | 0 - 60 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
63
  | Mobile-VIT | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.178 ms | 0 - 59 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.onnx) |
64
+ | Mobile-VIT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 3.198 ms | 0 - 47 MB | NPU | [Mobile-VIT.tflite](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.tflite) |
65
  | Mobile-VIT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.809 ms | 1 - 53 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
66
  | Mobile-VIT | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.586 ms | 0 - 50 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.onnx) |
67
  | Mobile-VIT | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.794 ms | 37 - 37 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.dlc) |
68
  | Mobile-VIT | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 4.979 ms | 12 - 12 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT.onnx) |
69
+ | Mobile-VIT | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.712 ms | 0 - 36 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
70
+ | Mobile-VIT | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.226 ms | 0 - 47 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
71
+ | Mobile-VIT | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.773 ms | 0 - 13 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
72
+ | Mobile-VIT | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.201 ms | 0 - 37 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
73
+ | Mobile-VIT | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 16.827 ms | 0 - 45 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
74
+ | Mobile-VIT | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 6.712 ms | 0 - 36 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
75
+ | Mobile-VIT | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 3.743 ms | 0 - 14 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
76
+ | Mobile-VIT | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 4.76 ms | 0 - 37 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
77
+ | Mobile-VIT | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 3.782 ms | 0 - 13 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
78
+ | Mobile-VIT | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.201 ms | 0 - 37 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
79
+ | Mobile-VIT | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.772 ms | 0 - 16 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
80
  | Mobile-VIT | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 13.588 ms | 14 - 76 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.onnx) |
81
+ | Mobile-VIT | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.443 ms | 0 - 49 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
82
  | Mobile-VIT | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.105 ms | 19 - 161 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.onnx) |
83
+ | Mobile-VIT | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.197 ms | 0 - 41 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
84
  | Mobile-VIT | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 7.002 ms | 19 - 136 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.onnx) |
85
+ | Mobile-VIT | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.259 ms | 0 - 0 MB | NPU | [Mobile-VIT.dlc](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.dlc) |
86
  | Mobile-VIT | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 13.174 ms | 29 - 29 MB | NPU | [Mobile-VIT.onnx](https://huggingface.co/qualcomm/Mobile-VIT/blob/main/Mobile-VIT_w8a16.onnx) |
87
 
88
 
 
141
  ```bash
142
  python -m qai_hub_models.models.mobile_vit.export
143
  ```
144
+
 
 
 
 
 
 
 
 
 
 
145
 
146
 
147
  ## How does this work?
precompiled/qualcomm-snapdragon-x-elite/Mobile-VIT.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:979f8aba238297e1059ec4aa41e2886bd06298d680dc99cece4bb077b19190b5
3
- size 10651037
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bebbbfa78e9b532f783d55933e31f5b3316cdd1282c58e70c6051146d09ca1ae
3
+ size 10651043
precompiled/qualcomm-snapdragon-x-elite/Mobile-VIT_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69a428e38f7cde17dbe492013f3dc4a06d66f5c10b4a256b16ab619adcff0e58
3
- size 5412668
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbaa5977993449c2657e2889b52865c54322519beb82887a63c7139b3d9ee7d9
3
+ size 5412669
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