Profile Job Results
Jobs
jp8x728xg
Results Ready
Name
edgetam_video_decoder
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
sparse_embedding: float32[1, 3, 256]image_embeddings: float32[1, 64, 64, 256]high_res_features2: float32[1, 128, 128, 64]high_res_features1: float32[1, 256, 256, 32]Completion Time
8/22/2026, 1:52:10 PM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
6.58 ms
Estimated Peak Memory Usage
16 ‑ 35 MB
Compute Units
NPU
864
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.98 s | 214‑215 MB |
Subsequent App Load | 176 ms | 2 MB |
Inference | 6.58 ms | 16‑35 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