Profile Job Results
Jobs
jp0kn3me5
Results Ready
Name
edgetam_memory_encoder
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
mask_for_mem: uint8[1, 1, 1024, 1024]pix_feat: uint8[1, 256, 64, 64]Completion Time
6/14/2026, 2:51:58 AM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.06.08.2
Estimated Inference Time
18.2 ms
Estimated Peak Memory Usage
1 ‑ 5 MB
Compute Units
NPU
269
| Stage | Time | Memory |
|---|---|---|
First App Load | 28.2 s | 270‑271 MB |
Subsequent App Load | 211 ms | 1‑2 MB |
Inference | 18.2 ms | 1‑5 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 | 2.0 |
| 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