Profile Job Results
Jobs
jgdq4x4e5
Results Ready
Name
convnext_tiny
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 3, 224, 224]Completion Time
9/7/2025, 1:27:25 AM
Options
--qairt_version 2.36Versions
- ONNX Runtime: 1.22.0
- QAIRT: v2.36.4.250725200057_123280
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.08.28.0
Estimated Inference Time
2.90 ms
Estimated Peak Memory Usage
0 ‑ 79 MB
Compute Units
NPU
198
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.19 s | 464‑465 MB |
Subsequent App Load | 3.55 s | 501‑504 MB |
Inference | 2.90 ms | 0‑79 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device