Profile Job Results
Jobs
j57lz3zng
Results Ready
Name
convnext_tiny
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 3, 224, 224]Completion Time
9/28/2025, 10:14:49 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.22.2
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
210 ms
Estimated Peak Memory Usage
33 ‑ 48 MB
Compute Units
CPU
656
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.60 s | 79‑89 MB |
Subsequent App Load | 2.24 s | 0‑16 MB |
Inference | 210 ms | 33‑48 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device