Profile Job Results
Jobs
jpx11q09g
Results Ready
Name
detectron2_detection_w8a8_Detectron2ROIHead
Target Device
- Snapdragon 8 Elite Gen 5 QRD
- Android 16
- Snapdragon® 8 Elite Gen 5 | SM8850
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
features: uint8[1, 1024, 50, 50]proposals_boxes: uint8[1, 200, 4]Completion Time
2/1/2026, 9:25:38 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- QAIRT: v2.37.1.250807093845_124904
- Android: 16 (BQ2A.251217.002-BP2A.250705.008)
- Build ID: Kaanapali.LA.1.0.r1-01100-STD.PROD-1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
68.3 ms
Estimated Peak Memory Usage
408 ‑ 704 MB
Compute Units
NPU
160
CPU
6
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.01 s | 405‑412 MB |
Subsequent App Load | 104 ms | 0‑297 MB |
Inference | 68.3 ms | 408‑704 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