Profile Job Results
Jobs
jp381dyz5
Results Ready
Name
edgetam_memory_encoder
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
pix_feat: float32[1, 256, 64, 64]mask_for_mem: float32[1, 1, 1024, 1024]Completion Time
5/31/2026, 5:54:33 PM
Versions
- LiteRT: 1.4.3
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 14 (UAG2.240908.001)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
- AI Hub: aihub-2026.05.27.0
Estimated Inference Time
28.7 ms
Estimated Peak Memory Usage
0 ‑ 324 MB
Compute Units
NPU
435
| Stage | Time | Memory |
|---|---|---|
First App Load | 30.1 s | 383‑388 MB |
Subsequent App Load | 388 ms | 7‑332 MB |
Inference | 28.7 ms | 0‑324 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
| htp_options.device_id | 1 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device