Profile Job Results
Jobs
jp39ek2xp
Results Ready
Name
sam3_head
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
backbone_fpn_0: float32[1, 256, 288, 288]tokenized: int32[1, 32]backbone_fpn_2: float32[1, 256, 72, 72]backbone_fpn_1: float32[1, 256, 144, 144]Completion Time
8/22/2026, 10:51:30 AM
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
491 ms
Estimated Peak Memory Usage
106 ‑ 278 MB
Compute Units
NPU
2304
| Stage | Time | Memory |
|---|---|---|
First App Load | 948 ms | 2‑3 MB |
Subsequent App Load | 890 ms | 2‑3 MB |
Inference | 491 ms | 106‑278 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