Profile Job Results
Jobs
jgz4jwz6p
Results Ready
Name
efficientnet_b0
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
7/5/2026, 5:29:51 PM
Versions
- LiteRT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
1.54 ms
Estimated Peak Memory Usage
0 ‑ 77 MB
Compute Units
NPU
245
| Stage | Time | Memory |
|---|---|---|
First App Load | 766 ms | 82‑84 MB |
Subsequent App Load | 206 ms | 15‑92 MB |
Inference | 1.54 ms | 0‑77 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