Profile Job Results
Jobs
jp2oyw4rg
Results Ready
Name
segformer_base
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 512, 512, 3]Completion Time
10/4/2026, 12:59:39 AM
Versions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
9.31 ms
Estimated Peak Memory Usage
2 ‑ 11 MB
Compute Units
NPU
639
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.32 s | 157‑158 MB |
Subsequent App Load | 222 ms | 1‑28 MB |
Inference | 9.31 ms | 2‑11 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device