Profile Job Results
Jobs
jgzzdvm4g
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
sparse_embedding: uint8[1, 3, 256]image_embeddings: uint8[1, 64, 64, 256]high_res_features2: uint8[1, 128, 128, 64]high_res_features1: uint8[1, 256, 256, 32]Completion Time
10/3/2026, 7:34:25 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
7.69 ms
Estimated Peak Memory Usage
3 ‑ 9 MB
Compute Units
NPU
853
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.46 s | 152‑153 MB |
Subsequent App Load | 186 ms | 2‑3 MB |
Inference | 7.69 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