Hugging Face's logo

qualcomm
/
SigLIP2

Image Classification
PyTorch
foundation
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
ab2d881
·
verified ·
1 Parent(s): 943dbe6

v0.63.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.

Files changed (2) hide show
  1. README.md +142 -154
  2. release_assets.json +11 -11
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  SigLIP2 (Sigmoid Loss for Language-Image Pre-training 2) is a vision-language model from Google that computes cosine-similarity scores between images and text prompts. It can be used for zero-shot image classification, image search, and content moderation without any task-specific fine-tuning.
16
 
17
  This is based on the implementation of SigLIP2 found [here](https://huggingface.co/google/siglip2-base-patch16-224).
18
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/siglip2) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
@@ -28,25 +28,25 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-onnx-w8a16.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-qnn_dlc-w8a16.zip)
35
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[SigLIP2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/siglip2)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/siglip2) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
- See our repository for [SigLIP2 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/siglip2) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -64,158 +64,146 @@ See our repository for [SigLIP2 on GitHub](https://github.com/qualcomm/ai-hub-mo
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | image_encoder | ONNX | float | Snapdragon® X2 Elite | 4.738 ms | 2 - 2 MB | NPU
68
- | image_encoder | ONNX | float | Snapdragon® X Elite | 8.828 ms | 182 - 182 MB | NPU
69
- | image_encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.893 ms | 1 - 311 MB | NPU
70
- | image_encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 13.248 ms | 1 - 294 MB | NPU
71
- | image_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 11.923 ms | 0 - 4 MB | NPU
72
- | image_encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.445 ms | 0 - 613 MB | NPU
73
- | image_encoder | ONNX | float | Qualcomm® QCS8450 | 13.248 ms | 1 - 294 MB | NPU
74
- | image_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 11.472 ms | 0 - 4 MB | NPU
75
- | image_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.828 ms | 182 - 182 MB | NPU
76
- | image_encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.241 ms | 0 - 176 MB | NPU
77
- | image_encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 4.241 ms | 0 - 176 MB | NPU
78
- | image_encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.262 ms | 1 - 167 MB | NPU
79
- | image_encoder | ONNX | w8a16 | Snapdragon® X2 Elite | 3.05 ms | 1 - 1 MB | NPU
80
- | image_encoder | ONNX | w8a16 | Snapdragon® X Elite | 5.544 ms | 91 - 91 MB | NPU
81
- | image_encoder | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.675 ms | 0 - 290 MB | NPU
82
- | image_encoder | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.195 ms | 0 - 280 MB | NPU
83
- | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 23.34 ms | 2 - 5 MB | NPU
84
- | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.066 ms | 0 - 4 MB | NPU
85
- | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.282 ms | 0 - 98 MB | NPU
86
- | image_encoder | ONNX | w8a16 | Qualcomm® QCS8450 | 7.195 ms | 0 - 280 MB | NPU
87
- | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.258 ms | 0 - 3 MB | NPU
88
- | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.544 ms | 91 - 91 MB | NPU
89
- | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 53.198 ms | 0 - 395 MB | NPU
90
- | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 6.998 ms | 0 - 270 MB | NPU
91
- | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.837 ms | 0 - 236 MB | NPU
92
- | image_encoder | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.837 ms | 0 - 236 MB | NPU
93
- | image_encoder | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.083 ms | 0 - 238 MB | NPU
94
- | image_encoder | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.998 ms | 0 - 270 MB | NPU
95
- | image_encoder | QNN_DLC | float | Snapdragon® X2 Elite | 3.989 ms | 1 - 1 MB | NPU
96
- | image_encoder | QNN_DLC | float | Snapdragon® X Elite | 9.205 ms | 1 - 1 MB | NPU
97
- | image_encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 6.047 ms | 0 - 264 MB | NPU
98
- | image_encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.512 ms | 0 - 243 MB | NPU
99
- | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.117 ms | 1 - 4 MB | NPU
100
- | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.574 ms | 1 - 3 MB | NPU
101
- | image_encoder | QNN_DLC | float | Qualcomm® SA8775P | 11.417 ms | 1 - 175 MB | NPU
102
- | image_encoder | QNN_DLC | float | Qualcomm® SA8650P | 11.417 ms | 1 - 175 MB | NPU
103
- | image_encoder | QNN_DLC | float | Qualcomm® SA8255P | 11.417 ms | 1 - 175 MB | NPU
104
- | image_encoder | QNN_DLC | float | Qualcomm® QCS8450 | 13.512 ms | 0 - 243 MB | NPU
105
- | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 11.475 ms | 1 - 3 MB | NPU
106
- | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 9.205 ms | 1 - 1 MB | NPU
107
- | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.242 ms | 0 - 176 MB | NPU
108
- | image_encoder | QNN_DLC | float | Qualcomm® SA7255P | 36.986 ms | 1 - 174 MB | NPU
109
- | image_encoder | QNN_DLC | float | Qualcomm® SA8295P | 14.146 ms | 1 - 150 MB | NPU
110
- | image_encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.242 ms | 0 - 176 MB | NPU
111
- | image_encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.396 ms | 1 - 164 MB | NPU
112
- | image_encoder | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 4.005 ms | 0 - 0 MB | NPU
113
- | image_encoder | QNN_DLC | w8a16 | Snapdragon® X Elite | 9.137 ms | 0 - 0 MB | NPU
114
- | image_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.545 ms | 0 - 311 MB | NPU
115
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 7.5 ms | 0 - 3 MB | NPU
116
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.443 ms | 0 - 282 MB | NPU
117
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® SA8775P | 8.664 ms | 0 - 255 MB | NPU
118
  | image_encoder | QNN_DLC | w8a16 | Qualcomm® SA8650P | 8.664 ms | 0 - 255 MB | NPU
119
  | image_encoder | QNN_DLC | w8a16 | Qualcomm® SA8255P | 8.664 ms | 0 - 255 MB | NPU
120
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.445 ms | 2 - 4 MB | NPU
121
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 9.137 ms | 0 - 0 MB | NPU
122
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 92.12 ms | 0 - 419 MB | NPU
123
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 13.929 ms | 0 - 402 MB | NPU
124
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.478 ms | 0 - 254 MB | NPU
125
- | image_encoder | QNN_DLC | w8a16 | Qualcomm® SA7255P | 19.111 ms | 0 - 253 MB | NPU
126
- | image_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 4.478 ms | 0 - 254 MB | NPU
127
- | image_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.28 ms | 0 - 257 MB | NPU
128
- | image_encoder | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 13.929 ms | 0 - 402 MB | NPU
129
- | image_encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.92 ms | 0 - 263 MB | NPU
130
- | image_encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 13.235 ms | 0 - 241 MB | NPU
131
- | image_encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 11.996 ms | 0 - 184 MB | NPU
132
- | image_encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.398 ms | 0 - 2 MB | NPU
133
- | image_encoder | TFLITE | float | Qualcomm® SA8775P | 11.269 ms | 0 - 176 MB | NPU
134
- | image_encoder | TFLITE | float | Qualcomm® SA8650P | 11.269 ms | 0 - 176 MB | NPU
135
- | image_encoder | TFLITE | float | Qualcomm® SA8255P | 11.269 ms | 0 - 176 MB | NPU
136
- | image_encoder | TFLITE | float | Qualcomm® QCS8450 | 13.235 ms | 0 - 241 MB | NPU
137
- | image_encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 11.364 ms | 0 - 184 MB | NPU
138
- | image_encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.16 ms | 0 - 180 MB | NPU
139
- | image_encoder | TFLITE | float | Qualcomm® SA7255P | 36.747 ms | 0 - 175 MB | NPU
140
- | image_encoder | TFLITE | float | Qualcomm® SA8295P | 13.923 ms | 0 - 161 MB | NPU
141
- | image_encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.16 ms | 0 - 180 MB | NPU
142
- | image_encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.297 ms | 0 - 170 MB | NPU
143
- | text_encoder | ONNX | float | Snapdragon® X2 Elite | 1.39 ms | 1 - 1 MB | NPU
144
- | text_encoder | ONNX | float | Snapdragon® X Elite | 2.9 ms | 542 - 542 MB | NPU
145
- | text_encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.752 ms | 0 - 251 MB | NPU
146
- | text_encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 4.465 ms | 0 - 244 MB | NPU
147
- | text_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 3.753 ms | 0 - 4 MB | NPU
148
- | text_encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.513 ms | 0 - 643 MB | NPU
149
- | text_encoder | ONNX | float | Qualcomm® QCS8450 | 4.465 ms | 0 - 244 MB | NPU
150
- | text_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 3.519 ms | 0 - 3 MB | NPU
151
- | text_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.9 ms | 542 - 542 MB | NPU
152
- | text_encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.409 ms | 0 - 138 MB | NPU
153
- | text_encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 2.409 ms | 0 - 138 MB | NPU
154
- | text_encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.405 ms | 0 - 140 MB | NPU
155
- | text_encoder | ONNX | w8a16 | Snapdragon® X2 Elite | 0.834 ms | 1 - 1 MB | NPU
156
- | text_encoder | ONNX | w8a16 | Snapdragon® X Elite | 1.722 ms | 460 - 460 MB | NPU
157
- | text_encoder | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.453 ms | 0 - 272 MB | NPU
158
- | text_encoder | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 2.832 ms | 0 - 276 MB | NPU
159
- | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 8.105 ms | 0 - 3 MB | NPU
160
- | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 2.051 ms | 0 - 3 MB | NPU
161
- | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.866 ms | 0 - 514 MB | NPU
162
- | text_encoder | ONNX | w8a16 | Qualcomm® QCS8450 | 2.832 ms | 0 - 276 MB | NPU
163
- | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 2.189 ms | 0 - 3 MB | NPU
164
- | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.722 ms | 460 - 460 MB | NPU
165
- | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 13.234 ms | 0 - 258 MB | NPU
166
- | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 2.847 ms | 0 - 239 MB | NPU
167
- | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1.268 ms | 0 - 231 MB | NPU
168
- | text_encoder | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 1.268 ms | 0 - 231 MB | NPU
169
- | text_encoder | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.245 ms | 0 - 234 MB | NPU
170
- | text_encoder | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.847 ms | 0 - 239 MB | NPU
171
- | text_encoder | QNN_DLC | float | Snapdragon® X2 Elite | 1.757 ms | 0 - 0 MB | NPU
172
- | text_encoder | QNN_DLC | float | Snapdragon® X Elite | 3.062 ms | 0 - 0 MB | NPU
173
- | text_encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.686 ms | 0 - 249 MB | NPU
174
- | text_encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 4.467 ms | 0 - 237 MB | NPU
175
- | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 3.743 ms | 0 - 2 MB | NPU
176
- | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.499 ms | 0 - 2 MB | NPU
177
- | text_encoder | QNN_DLC | float | Qualcomm® SA8775P | 3.655 ms | 0 - 133 MB | NPU
178
- | text_encoder | QNN_DLC | float | Qualcomm® SA8650P | 3.655 ms | 0 - 133 MB | NPU
179
- | text_encoder | QNN_DLC | float | Qualcomm® SA8255P | 3.655 ms | 0 - 133 MB | NPU
180
- | text_encoder | QNN_DLC | float | Qualcomm® QCS8450 | 4.467 ms | 0 - 237 MB | NPU
181
- | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 3.505 ms | 2 - 4 MB | NPU
182
- | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.062 ms | 0 - 0 MB | NPU
183
- | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.401 ms | 0 - 134 MB | NPU
184
- | text_encoder | QNN_DLC | float | Qualcomm® SA7255P | 10.029 ms | 0 - 134 MB | NPU
185
- | text_encoder | QNN_DLC | float | Qualcomm® SA8295P | 4.649 ms | 0 - 123 MB | NPU
186
- | text_encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.401 ms | 0 - 134 MB | NPU
187
- | text_encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.388 ms | 0 - 137 MB | NPU
188
- | text_encoder | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.052 ms | 1 - 1 MB | NPU
189
  | text_encoder | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.945 ms | 0 - 0 MB | NPU
190
- | text_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.456 ms | 0 - 261 MB | NPU
191
- | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 2.067 ms | 0 - 2 MB | NPU
192
- | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.909 ms | 0 - 955 MB | NPU
193
- | text_encoder | QNN_DLC | w8a16 | Qualcomm® SA8775P | 2.216 ms | 0 - 226 MB | NPU
194
  | text_encoder | QNN_DLC | w8a16 | Qualcomm® SA8650P | 2.216 ms | 0 - 226 MB | NPU
195
  | text_encoder | QNN_DLC | w8a16 | Qualcomm® SA8255P | 2.216 ms | 0 - 226 MB | NPU
196
- | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 2.078 ms | 0 - 2 MB | NPU
197
  | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.945 ms | 0 - 0 MB | NPU
198
- | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 13.635 ms | 0 - 261 MB | NPU
199
- | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 2.825 ms | 0 - 237 MB | NPU
200
- | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1.281 ms | 0 - 227 MB | NPU
201
- | text_encoder | QNN_DLC | w8a16 | Qualcomm® SA7255P | 4.02 ms | 0 - 226 MB | NPU
202
- | text_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 1.281 ms | 0 - 227 MB | NPU
203
- | text_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.254 ms | 0 - 229 MB | NPU
204
- | text_encoder | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.825 ms | 0 - 237 MB | NPU
205
- | text_encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.737 ms | 0 - 253 MB | NPU
206
- | text_encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 4.461 ms | 0 - 244 MB | NPU
207
- | text_encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 3.779 ms | 0 - 543 MB | NPU
208
- | text_encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.502 ms | 0 - 3 MB | NPU
209
- | text_encoder | TFLITE | float | Qualcomm® SA8775P | 3.699 ms | 0 - 142 MB | NPU
210
- | text_encoder | TFLITE | float | Qualcomm® SA8650P | 3.699 ms | 0 - 142 MB | NPU
211
- | text_encoder | TFLITE | float | Qualcomm® SA8255P | 3.699 ms | 0 - 142 MB | NPU
212
- | text_encoder | TFLITE | float | Qualcomm® QCS8450 | 4.461 ms | 0 - 244 MB | NPU
213
- | text_encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 3.526 ms | 0 - 543 MB | NPU
214
- | text_encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.412 ms | 0 - 146 MB | NPU
215
- | text_encoder | TFLITE | float | Qualcomm® SA7255P | 10.064 ms | 0 - 143 MB | NPU
216
- | text_encoder | TFLITE | float | Qualcomm® SA8295P | 4.671 ms | 0 - 129 MB | NPU
217
- | text_encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.412 ms | 0 - 146 MB | NPU
218
- | text_encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.403 ms | 0 - 146 MB | NPU
219
 
220
  ## License
221
  * The license for the original implementation of SigLIP2 can be found
 
15
  SigLIP2 (Sigmoid Loss for Language-Image Pre-training 2) is a vision-language model from Google that computes cosine-similarity scores between images and text prompts. It can be used for zero-shot image classification, image search, and content moderation without any task-specific fine-tuning.
16
 
17
  This is based on the implementation of SigLIP2 found [here](https://huggingface.co/google/siglip2-base-patch16-224).
18
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/siglip2) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-onnx-w8a16.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-qnn_dlc-w8a16.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[SigLIP2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/siglip2)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/siglip2) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
+ See our repository for [SigLIP2 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/siglip2) for usage instructions.
50
 
51
  ## Model Details
52
 
 
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
+ | image_encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.338 ms | 1 - 169 MB | NPU
68
+ | image_encoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.189 ms | 0 - 168 MB | NPU
69
+ | image_encoder | ONNX | float | Snapdragon® X2 Elite | 3.53 ms | 2 - 2 MB | NPU
70
+ | image_encoder | ONNX | float | Snapdragon® X Elite | 8.735 ms | 182 - 182 MB | NPU
71
+ | image_encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.814 ms | 1 - 304 MB | NPU
72
+ | image_encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 12.987 ms | 1 - 294 MB | NPU
73
+ | image_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 11.854 ms | 0 - 5 MB | NPU
74
+ | image_encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.332 ms | 0 - 194 MB | NPU
75
+ | image_encoder | ONNX | float | Qualcomm® QCS8450 | 12.987 ms | 1 - 294 MB | NPU
76
+ | image_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 11.318 ms | 0 - 4 MB | NPU
77
+ | image_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.735 ms | 182 - 182 MB | NPU
78
+ | image_encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.189 ms | 0 - 168 MB | NPU
79
+ | image_encoder | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.116 ms | 0 - 194 MB | NPU
80
+ | image_encoder | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.845 ms | 0 - 192 MB | NPU
81
+ | image_encoder | ONNX | w8a16 | Snapdragon® X2 Elite | 2.357 ms | 1 - 1 MB | NPU
82
+ | image_encoder | ONNX | w8a16 | Snapdragon® X Elite | 5.535 ms | 91 - 91 MB | NPU
83
+ | image_encoder | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.683 ms | 0 - 295 MB | NPU
84
+ | image_encoder | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 7.156 ms | 0 - 285 MB | NPU
85
+ | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 18.752 ms | 2 - 5 MB | NPU
86
+ | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.086 ms | 0 - 4 MB | NPU
87
+ | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.28 ms | 0 - 98 MB | NPU
88
+ | image_encoder | ONNX | w8a16 | Qualcomm® QCS8450 | 7.156 ms | 0 - 285 MB | NPU
89
+ | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.249 ms | 0 - 4 MB | NPU
90
+ | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.535 ms | 91 - 91 MB | NPU
91
+ | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 53.641 ms | 0 - 376 MB | NPU
92
+ | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 6.972 ms | 0 - 256 MB | NPU
93
+ | image_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.845 ms | 0 - 192 MB | NPU
94
+ | image_encoder | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.972 ms | 0 - 256 MB | NPU
95
+ | image_encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.421 ms | 1 - 166 MB | NPU
96
+ | image_encoder | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.237 ms | 0 - 163 MB | NPU
97
+ | image_encoder | QNN_DLC | float | Snapdragon® X2 Elite | 3.903 ms | 1 - 1 MB | NPU
98
+ | image_encoder | QNN_DLC | float | Snapdragon® X Elite | 9.12 ms | 1 - 1 MB | NPU
99
+ | image_encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.954 ms | 0 - 253 MB | NPU
100
+ | image_encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.211 ms | 1 - 248 MB | NPU
101
+ | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.021 ms | 1 - 4 MB | NPU
102
+ | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.494 ms | 1 - 2 MB | NPU
103
+ | image_encoder | QNN_DLC | float | Qualcomm® QCS8450 | 13.211 ms | 1 - 248 MB | NPU
104
+ | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 11.246 ms | 1 - 3 MB | NPU
105
+ | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 9.12 ms | 1 - 1 MB | NPU
106
+ | image_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.237 ms | 0 - 163 MB | NPU
107
+ | image_encoder | QNN_DLC | float | Qualcomm® SA8295P | 13.937 ms | 1 - 153 MB | NPU
108
+ | image_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.46 ms | 0 - 183 MB | NPU
109
+ | image_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.306 ms | 0 - 179 MB | NPU
110
+ | image_encoder | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.04 ms | 0 - 0 MB | NPU
111
+ | image_encoder | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.828 ms | 0 - 0 MB | NPU
112
+ | image_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.255 ms | 0 - 287 MB | NPU
113
+ | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.823 ms | 0 - 3 MB | NPU
114
+ | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.294 ms | 0 - 2 MB | NPU
 
 
 
115
  | image_encoder | QNN_DLC | w8a16 | Qualcomm® SA8650P | 8.664 ms | 0 - 255 MB | NPU
116
  | image_encoder | QNN_DLC | w8a16 | Qualcomm® SA8255P | 8.664 ms | 0 - 255 MB | NPU
117
+ | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.231 ms | 0 - 3 MB | NPU
118
+ | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.828 ms | 0 - 0 MB | NPU
119
+ | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 65.954 ms | 0 - 361 MB | NPU
120
+ | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 7.864 ms | 0 - 262 MB | NPU
121
+ | image_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.306 ms | 0 - 179 MB | NPU
122
+ | image_encoder | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.864 ms | 0 - 262 MB | NPU
123
+ | image_encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.299 ms | 0 - 169 MB | NPU
124
+ | image_encoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.108 ms | 0 - 165 MB | NPU
125
+ | image_encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.881 ms | 0 - 252 MB | NPU
126
+ | image_encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 12.937 ms | 0 - 244 MB | NPU
127
+ | image_encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12.057 ms | 0 - 185 MB | NPU
128
+ | image_encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.95 ms | 0 - 3 MB | NPU
129
+ | image_encoder | TFLITE | float | Qualcomm® SA8775P | 11.177 ms | 0 - 163 MB | NPU
130
+ | image_encoder | TFLITE | float | Qualcomm® SA8650P | 11.177 ms | 0 - 163 MB | NPU
131
+ | image_encoder | TFLITE | float | Qualcomm® SA8255P | 11.177 ms | 0 - 163 MB | NPU
132
+ | image_encoder | TFLITE | float | Qualcomm® QCS8450 | 12.937 ms | 0 - 244 MB | NPU
133
+ | image_encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 10.971 ms | 0 - 184 MB | NPU
134
+ | image_encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.108 ms | 0 - 165 MB | NPU
135
+ | image_encoder | TFLITE | float | Qualcomm® SA7255P | 400.273 ms | 0 - 11 MB | CPU
136
+ | image_encoder | TFLITE | float | Qualcomm® SA8295P | 13.752 ms | 0 - 151 MB | NPU
137
+ | text_encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.41 ms | 0 - 144 MB | NPU
138
+ | text_encoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.419 ms | 0 - 144 MB | NPU
139
+ | text_encoder | ONNX | float | Snapdragon® X2 Elite | 1.406 ms | 1 - 1 MB | NPU
140
+ | text_encoder | ONNX | float | Snapdragon® X Elite | 2.899 ms | 543 - 543 MB | NPU
141
+ | text_encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.723 ms | 0 - 255 MB | NPU
142
+ | text_encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 4.081 ms | 0 - 249 MB | NPU
143
+ | text_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 3.771 ms | 0 - 4 MB | NPU
144
+ | text_encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.526 ms | 0 - 643 MB | NPU
145
+ | text_encoder | ONNX | float | Qualcomm® QCS8450 | 4.081 ms | 0 - 249 MB | NPU
146
+ | text_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 3.515 ms | 0 - 3 MB | NPU
147
+ | text_encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.899 ms | 543 - 543 MB | NPU
148
+ | text_encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.419 ms | 0 - 144 MB | NPU
149
+ | text_encoder | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.235 ms | 0 - 192 MB | NPU
150
+ | text_encoder | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.247 ms | 0 - 190 MB | NPU
151
+ | text_encoder | ONNX | w8a16 | Snapdragon® X2 Elite | 0.757 ms | 1 - 1 MB | NPU
152
+ | text_encoder | ONNX | w8a16 | Snapdragon® X Elite | 1.676 ms | 459 - 459 MB | NPU
153
+ | text_encoder | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.452 ms | 0 - 277 MB | NPU
154
+ | text_encoder | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 2.223 ms | 0 - 279 MB | NPU
155
+ | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 6.553 ms | 0 - 3 MB | NPU
156
+ | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 2.078 ms | 0 - 4 MB | NPU
157
+ | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.853 ms | 0 - 515 MB | NPU
158
+ | text_encoder | ONNX | w8a16 | Qualcomm® QCS8450 | 2.223 ms | 0 - 279 MB | NPU
159
+ | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 2.193 ms | 0 - 3 MB | NPU
160
+ | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.676 ms | 459 - 459 MB | NPU
161
+ | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 13.139 ms | 0 - 249 MB | NPU
162
+ | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 2.859 ms | 0 - 243 MB | NPU
163
+ | text_encoder | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1.247 ms | 0 - 190 MB | NPU
164
+ | text_encoder | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.859 ms | 0 - 243 MB | NPU
165
+ | text_encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.394 ms | 0 - 139 MB | NPU
166
+ | text_encoder | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.431 ms | 0 - 139 MB | NPU
167
+ | text_encoder | QNN_DLC | float | Snapdragon® X2 Elite | 1.695 ms | 0 - 0 MB | NPU
168
+ | text_encoder | QNN_DLC | float | Snapdragon® X Elite | 3.072 ms | 0 - 0 MB | NPU
169
+ | text_encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.704 ms | 0 - 251 MB | NPU
170
+ | text_encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 4.066 ms | 0 - 243 MB | NPU
171
+ | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 3.745 ms | 0 - 3 MB | NPU
172
+ | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.525 ms | 0 - 2 MB | NPU
173
+ | text_encoder | QNN_DLC | float | Qualcomm® QCS8450 | 4.066 ms | 0 - 243 MB | NPU
174
+ | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 3.52 ms | 0 - 2 MB | NPU
175
+ | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.072 ms | 0 - 0 MB | NPU
176
+ | text_encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.431 ms | 0 - 139 MB | NPU
177
+ | text_encoder | QNN_DLC | float | Qualcomm® SA8295P | 4.508 ms | 0 - 129 MB | NPU
178
+ | text_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.232 ms | 0 - 186 MB | NPU
179
+ | text_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.276 ms | 0 - 186 MB | NPU
180
+ | text_encoder | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.979 ms | 1 - 1 MB | NPU
 
 
 
 
 
181
  | text_encoder | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.945 ms | 0 - 0 MB | NPU
182
+ | text_encoder | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.46 ms | 0 - 268 MB | NPU
183
+ | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 2.063 ms | 0 - 3 MB | NPU
184
+ | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.868 ms | 0 - 2 MB | NPU
 
185
  | text_encoder | QNN_DLC | w8a16 | Qualcomm® SA8650P | 2.216 ms | 0 - 226 MB | NPU
186
  | text_encoder | QNN_DLC | w8a16 | Qualcomm® SA8255P | 2.216 ms | 0 - 226 MB | NPU
187
+ | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 2.068 ms | 0 - 2 MB | NPU
188
  | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.945 ms | 0 - 0 MB | NPU
189
+ | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 13.676 ms | 0 - 247 MB | NPU
190
+ | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 2.956 ms | 0 - 241 MB | NPU
191
+ | text_encoder | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1.276 ms | 0 - 186 MB | NPU
192
+ | text_encoder | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.956 ms | 0 - 241 MB | NPU
193
+ | text_encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.414 ms | 0 - 151 MB | NPU
194
+ | text_encoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.406 ms | 0 - 151 MB | NPU
195
+ | text_encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.741 ms | 0 - 261 MB | NPU
196
+ | text_encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 4.081 ms | 0 - 246 MB | NPU
197
+ | text_encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 3.821 ms | 0 - 544 MB | NPU
198
+ | text_encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.515 ms | 0 - 2 MB | NPU
199
+ | text_encoder | TFLITE | float | Qualcomm® SA8775P | 3.688 ms | 0 - 145 MB | NPU
200
+ | text_encoder | TFLITE | float | Qualcomm® SA8650P | 3.688 ms | 0 - 145 MB | NPU
201
+ | text_encoder | TFLITE | float | Qualcomm® SA8255P | 3.688 ms | 0 - 145 MB | NPU
202
+ | text_encoder | TFLITE | float | Qualcomm® QCS8450 | 4.081 ms | 0 - 246 MB | NPU
203
+ | text_encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 3.528 ms | 0 - 543 MB | NPU
204
+ | text_encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.406 ms | 0 - 151 MB | NPU
205
+ | text_encoder | TFLITE | float | Qualcomm® SA7255P | 107.151 ms | 0 - 29 MB | GPU
206
+ | text_encoder | TFLITE | float | Qualcomm® SA8295P | 4.537 ms | 0 - 132 MB | NPU
 
 
 
207
 
208
  ## License
209
  * The license for the original implementation of SigLIP2 can be found
release_assets.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "version": "0.62.2",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
- "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
- "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
- "qairt": "2.45.0.260326154327"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -28,16 +28,16 @@
28
  "universal_assets": {
29
  "onnx": {
30
  "tool_versions": {
31
- "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-onnx-w8a16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
- "qairt": "2.45.0.260326154327"
39
  },
40
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.62.2/siglip2-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }
 
1
  {
2
+ "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
+ "qairt": "2.50.0.260828221209",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
+ "qairt": "2.50.0.260828221209"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
+ "qairt": "2.50.0.260828221209"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-tflite-float.zip"
24
  }
25
  }
26
  },
 
28
  "universal_assets": {
29
  "onnx": {
30
  "tool_versions": {
31
+ "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-onnx-w8a16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
+ "qairt": "2.50.0.260828221209"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/siglip2/releases/v0.63.0/siglip2-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }