Profile Job Results
Jobs
jp841knx5
Results Ready
Name
efficientnet_lite4
Target Device
- Dragonwing Q-6690 MTP
- Android 15
- Qualcomm® Dragonwing™ Q-6690 | QCM6690
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: uint8[1, 300, 300, 3]Completion Time
7/13/2026, 11:38:01 PM
Versions
- LiteRT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 15 (AQ3A.250330.001)
- Build ID: QCM6690.LA.1.0.r1-00117-STD.PROD-1
- AI Hub: aihub-2026.07.02.0
Estimated Inference Time
10.0 ms
Estimated Peak Memory Usage
0 ‑ 178 MB
Compute Units
NPU
123
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.82 s | 145‑153 MB |
Subsequent App Load | 227 ms | 34‑215 MB |
Inference | 10.0 ms | 0‑178 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