Profile Job Results
Jobs
jpxlm0nlp
Results Ready
Name
resnet50
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: uint8[1, 3, 224, 224]Completion Time
9/19/2026, 9:37:10 PM
Options
--qairt_version latestVersions
- ONNX Runtime: 1.27.1
- QAIRT: v2.50.0.260828221209
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
904 μs
Estimated Peak Memory Usage
0 ‑ 160 MB
Compute Units
NPU
80
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.37 s | 135‑136 MB |
Subsequent App Load | 401 ms | 1‑133 MB |
Inference | 904 μs | 0‑160 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