Profile Job Results
Jobs
jpelw4y0g
Results Ready
Name
edgetam_video_decoder
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
image_embeddings: uint8[1, 64, 64, 256]sparse_embedding: uint8[1, 3, 256]high_res_features2: uint8[1, 128, 128, 64]high_res_features1: uint8[1, 256, 256, 32]Completion Time
7/5/2026, 1:42:55 PM
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-2026.06.19.2
Estimated Inference Time
11.6 ms
Estimated Peak Memory Usage
3 ‑ 9 MB
Compute Units
NPU
851
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.32 s | 228‑229 MB |
Subsequent App Load | 184 ms | 3‑4 MB |
Inference | 11.6 ms | 3‑9 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