Profile Job Results
Jobs
jglkknl2p
Results Ready
Name
convnext_tiny_w8a16
Target Device
- Snapdragon 7 Gen 4 QRD
- Android 15
- Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 3, 224, 224]Completion Time
2/1/2026, 11:18:40 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- Android: 15 (AQ3A.250411.001)
- Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
232 ms
Estimated Peak Memory Usage
57 ‑ 71 MB
Compute Units
CPU
679
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.16 s | 59‑66 MB |
Subsequent App Load | 2.12 s | 1‑16 MB |
Inference | 232 ms | 57‑71 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