Views
No views yet

| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| QNN_CONTEXT_BINARY | mixed | Snapdragon® X2 Elite | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Snapdragon® X Elite | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8775P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Qualcomm® SA7255P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | Download |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X2 Elite | 13.776 ms | 35 - 35 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X Elite | 28.423 ms | 385 - 385 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Gen 3 Mobile | 22.661 ms | 35 - 47 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-8275 | 29.303 ms | 34 - 72 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 29.741 ms | 0 - 414 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-9075 | 30.501 ms | 34 - 72 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-X7181 | 28.423 ms | 385 - 385 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ Q-8750 | 16.835 ms | 16 - 27 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Mobile | 16.835 ms | 16 - 27 MB | NPU |
| action_expert | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Gen 5 Mobile | 14.7 ms | 30 - 43 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Snapdragon® X2 Elite | 14.513 ms | 34 - 34 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Snapdragon® X Elite | 28.581 ms | 34 - 34 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Gen 3 Mobile | 22.033 ms | 34 - 42 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | 28.913 ms | 34 - 71 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | 53.953 ms | 14 - 22 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 29.429 ms | 35 - 36 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8775P | 29.732 ms | 0 - 10 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8650P | 29.732 ms | 0 - 10 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8255P | 29.732 ms | 0 - 10 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-9075 | 30.961 ms | 34 - 70 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-X7181 | 28.581 ms | 34 - 34 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ Q-8750 | 17.159 ms | 15 - 24 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA7255P | 53.953 ms | 14 - 22 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Mobile | 17.159 ms | 15 - 24 MB | NPU |
| action_expert | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Gen 5 Mobile | 14.122 ms | 28 - 37 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X2 Elite | 249.894 ms | 131 - 131 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X Elite | 444.291 ms | 924 - 924 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Gen 3 Mobile | 332.842 ms | 85 - 95 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-8275 | 429.257 ms | 23 - 39 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 458.356 ms | 0 - 1013 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-9075 | 398.831 ms | 12 - 27 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-X7181 | 444.291 ms | 924 - 924 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ Q-8750 | 298.203 ms | 74 - 86 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Mobile | 298.203 ms | 74 - 86 MB | NPU |
| backbone | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Gen 5 Mobile | 272.077 ms | 74 - 85 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Snapdragon® X2 Elite | 250.205 ms | 12 - 12 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Snapdragon® X Elite | 447.549 ms | 12 - 12 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Gen 3 Mobile | 333.035 ms | 12 - 19 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | 428.595 ms | 12 - 61 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | 1092.262 ms | 3 - 13 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 458.312 ms | 13 - 14 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8775P | 403.971 ms | 4 - 13 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8650P | 403.971 ms | 4 - 13 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8255P | 403.971 ms | 4 - 13 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-9075 | 397.164 ms | 12 - 60 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-X7181 | 447.549 ms | 12 - 12 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ Q-8750 | 295.498 ms | 0 - 9 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA7255P | 1092.262 ms | 3 - 13 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Mobile | 295.498 ms | 0 - 9 MB | NPU |
| backbone | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Gen 5 Mobile | 269.876 ms | 4 - 14 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X2 Elite | 2.082 ms | 39 - 39 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X Elite | 3.648 ms | 1002 - 1002 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Gen 3 Mobile | 2.768 ms | 0 - 11 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-8275 | 4.384 ms | 6 - 16 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.612 ms | 0 - 1018 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-9075 | 4.337 ms | 6 - 15 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-X7181 | 3.648 ms | 1002 - 1002 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ Q-8750 | 2.888 ms | 1 - 14 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Mobile | 2.888 ms | 1 - 14 MB | NPU |
| token_emb | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Gen 5 Mobile | 2.194 ms | 2 - 15 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Snapdragon® X2 Elite | 2.392 ms | 6 - 6 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Snapdragon® X Elite | 3.472 ms | 6 - 6 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Gen 3 Mobile | 2.711 ms | 0 - 7 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | 4.314 ms | 6 - 27 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | 6.257 ms | 0 - 8 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.72 ms | 2 - 3 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8775P | 4.384 ms | 0 - 10 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8650P | 4.384 ms | 0 - 10 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8255P | 4.384 ms | 0 - 10 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-9075 | 4.27 ms | 6 - 26 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-X7181 | 3.472 ms | 6 - 6 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ Q-8750 | 2.792 ms | 0 - 10 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA7255P | 6.257 ms | 0 - 8 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Mobile | 2.792 ms | 0 - 10 MB | NPU |
| token_emb | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Gen 5 Mobile | 2.196 ms | 2 - 11 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X2 Elite | 16.839 ms | 5 - 5 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X Elite | 43.118 ms | 516 - 516 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Gen 3 Mobile | 27.646 ms | 5 - 16 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-8275 | 36.105 ms | 4 - 8 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 41.78 ms | 0 - 641 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-9075 | 50.99 ms | 4 - 7 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-X7181 | 43.118 ms | 516 - 516 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ Q-8750 | 21.369 ms | 5 - 17 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Mobile | 21.369 ms | 5 - 17 MB | NPU |
| vision_encoder | PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Gen 5 Mobile | 16.741 ms | 5 - 17 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Snapdragon® X2 Elite | 17.149 ms | 1 - 1 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Snapdragon® X Elite | 43.091 ms | 1 - 1 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Gen 3 Mobile | 27.584 ms | 1 - 8 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | 36.292 ms | 1 - 6 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | 84.485 ms | 1 - 10 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 41.663 ms | 1 - 2 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8775P | 39.945 ms | 1 - 10 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8650P | 39.945 ms | 1 - 10 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8255P | 39.945 ms | 1 - 10 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-9075 | 40.315 ms | 1 - 5 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-X7181 | 43.091 ms | 1 - 1 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ Q-8750 | 21.244 ms | 1 - 10 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Qualcomm® SA7255P | 84.485 ms | 1 - 10 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Mobile | 21.244 ms | 1 - 10 MB | NPU |
| vision_encoder | QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Gen 5 Mobile | 16.457 ms | 1 - 9 MB | NPU |