Profile Job Results
Jobs
jgl12ql25
Results Ready
Name
rangenet_plus_plus
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
range_image: float32[1, 64, 2048, 5]Completion Time
7/6/2026, 3:04:48 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
104 ms
Estimated Peak Memory Usage
10 ‑ 226 MB
Compute Units
NPU
174
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.46 s | 393‑394 MB |
Subsequent App Load | 323 ms | 0‑293 MB |
Inference | 104 ms | 10‑226 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