Profile Job Results
Jobs
jpr60y1kp
Results Ready
Name
convnext_tiny_w8a16_quantized
Target Device
- Samsung Galaxy S23 (Family)
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 3, 224, 224]Completion Time
3/11/2025, 9:26:24 PM
Versions
- ONNX Runtime: 1.20.1
- QAIRT: v2.32.0.250228225014_116386
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
83.5 ms
Estimated Peak Memory Usage
210 ‑ 361 MB
Compute Units
NPU
357
CPU
40
| Stage | Time | Memory |
|---|---|---|
First App Load | 46.4 s | 508‑510 MB |
Subsequent App Load | 44.7 s | 563‑567 MB |
Inference | 83.5 ms | 210‑361 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" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device