Profile Job Results
Jobs
jgneee8vg
Results Ready
Name
resnet_mixed_w8a16
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: uint16[1, 3, 16, 112, 112]Completion Time
1/31/2026, 10:01:09 PM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- QAIRT: v2.37.1.250807093845_124904
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
8.78 ms
Estimated Peak Memory Usage
0 ‑ 232 MB
Compute Units
NPU
46
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.33 s | 209‑210 MB |
Subsequent App Load | 179 ms | 13‑233 MB |
Inference | 8.78 ms | 0‑232 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