Profile Job Results
Jobs
jpry32m7g
Results Ready
Name
facemap_3dmm_w8a8
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
Target Model
Input Specs
image: uint8[1, 128, 128, 3]Completion Time
1/11/2026, 2:26:58 AM
Options
--qairt_version latestVersions
- QAIRT: v2.41.0.251128145156_191518
- QNN Backend API: 5.41.0
- QNN Core API: 2.31.0
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
693 μs
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
55
| Stage | Time | Memory |
|---|---|---|
First App Load | 549 ms | 176‑177 MB |
Subsequent App Load | 161 ms | 3‑4 MB |
Inference | 693 μs | 0‑2 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