Profile Job Results
Jobs
jp3w1qy35
Results Ready
Name
edgetam_memory_encoder
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
mask_for_mem: float32[1, 1, 1024, 1024]pix_feat: float32[1, 256, 64, 64]Completion Time
7/5/2026, 2:08:59 PM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
18.8 ms
Estimated Peak Memory Usage
8 ‑ 10 MB
Compute Units
NPU
301
| Stage | Time | Memory |
|---|---|---|
First App Load | 28.1 s | 508‑509 MB |
Subsequent App Load | 224 ms | 0‑57 MB |
Inference | 18.8 ms | 8‑10 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device