Profile Job Results
Jobs
jprx3kn9p
Results Ready
Name
wedetect_text_encoder
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[80, 16]attention_mask: int32[80, 16]Completion Time
10/4/2026, 10:14:36 AM
Versions
- ONNX Runtime: 1.30.0
- QAIRT: v2.50.0.260828221209
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
53.6 ms
Estimated Peak Memory Usage
0 ‑ 2 GB
Compute Units
NPU
355
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.62 min | 3 GB |
Subsequent App Load | 719 ms | 1‑3 GB |
Inference | 53.6 ms | 0‑2 GB |
| 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