Profile Job Results
Jobs
jprel8me5
Results Ready
Name
segformer_base_w8a16
Target Device
- RB5 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint16[1, 3, 512, 512]Completion Time
11/29/2025, 6:01:59 PM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.11.18.0
Estimated Inference Time
427 ms
Estimated Peak Memory Usage
369 ‑ 374 MB
Compute Units
CPU
912
| Stage | Time | Memory |
|---|---|---|
First App Load | 328 ms | 19‑21 MB |
Subsequent App Load | 299 ms | 12‑15 MB |
Inference | 427 ms | 369‑374 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