Profile Job Results
Jobs
j5q7mq3og
Results Ready
Name
depth_anything_v3
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 518, 518, 3]Completion Time
4/5/2026, 9:25:29 PM
Versions
- LiteRT: 1.4.2
- QAIRT: v2.43.0.260127150333_193827
- QNN TfLite Delegate: v2.43.0.260127150333_193827
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
67.3 ms
Estimated Peak Memory Usage
1 ‑ 5 MB
Compute Units
NPU
1075
| Stage | Time | Memory |
|---|---|---|
First App Load | 24.5 s | 594‑596 MB |
Subsequent App Load | 335 ms | 75‑752 MB |
Inference | 67.3 ms | 1‑5 MB |
| TensorFlow Lite | 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