Profile Job Results
Jobs
j5mw10k7p
Results Ready
Name
lama_dilated
Target Device
- QCS8450 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 512, 512, 3]mask: float32[1, 512, 512, 1]Completion Time
4/19/2026, 9:17:14 AM
Versions
- LiteRT: 1.4.2
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.04.13.0
Estimated Inference Time
135 ms
Estimated Peak Memory Usage
3 ‑ 453 MB
Compute Units
NPU
340
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.85 s | 536‑545 MB |
Subsequent App Load | 331 ms | 99‑551 MB |
Inference | 135 ms | 3‑453 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