Profile Job Results
Jobs
jp41qmnvp
Results Ready
Name
siglip2_text_encoder
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[1, 64]Completion Time
9/6/2026, 5:25:31 AM
Versions
- ONNX Runtime: 1.27.1
- QAIRT: v2.45.0.260326154327
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
1.87 ms
Estimated Peak Memory Usage
0 ‑ 514 MB
Compute Units
NPU
400
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.60 s | 2 GB |
Subsequent App Load | 791 ms | 459‑657 MB |
Inference | 1.87 ms | 0‑514 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device