Profile Job Results
Jobs
jgolml2qg
Results Ready
Name
mobile_facenet
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
img1: uint16[1, 3, 112, 112]img2: uint16[1, 3, 112, 112]Completion Time
9/19/2026, 8:46:12 PM
Options
--qairt_version latestVersions
- ONNX Runtime: 1.27.1
- QAIRT: v2.50.0.260828221209
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
879 μs
Estimated Peak Memory Usage
0 ‑ 4 MB
Compute Units
NPU
147
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.49 s | 64‑65 MB |
Subsequent App Load | 464 ms | 10‑11 MB |
Inference | 879 μs | 0‑4 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