Profile Job Results
Jobs
jpekwz3vp
Results Ready
Name
segformer_base_w8a16
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint16[1, 3, 512, 512]Completion Time
10/25/2025, 4:31:35 PM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
457 ms
Estimated Peak Memory Usage
374 ‑ 390 MB
Compute Units
CPU
912
| Stage | Time | Memory |
|---|---|---|
First App Load | 601 ms | 25‑36 MB |
Subsequent App Load | 551 ms | 13‑34 MB |
Inference | 457 ms | 374‑390 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