Profile Job Results
Jobs
jgj3nk71p
Results Ready
Name
edgetam_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
labels: uint8[1, 2]image: uint8[1, 1024, 1024, 3]unnorm_coords: uint8[1, 2, 2]Completion Time
10/3/2026, 7:37:51 PM
Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
2.79 s
Estimated Peak Memory Usage
3 ‑ 13 MB
Compute Units
NPU
300
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.12 s | 234‑235 MB |
Subsequent App Load | 280 ms | 2‑3 MB |
Inference | 2.79 s | 3‑13 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