Profile Job Results
Jobs
jgk2mmzwg
Results Ready
Name
convnext_base
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 224, 224, 3]Completion Time
10/3/2026, 11:28:29 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
7.35 ms
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
598
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.49 s | 462‑463 MB |
Subsequent App Load | 360 ms | 161‑257 MB |
Inference | 7.35 ms | 0‑2 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