Profile Job Results
Jobs
j5w4erk4g
Results Ready
Name
bevdet_encoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 18, 256, 704]Completion Time
7/25/2026, 9:16:14 PM
Versions
- Lite RT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.07.17.0
Estimated Inference Time
60.4 ms
Estimated Peak Memory Usage
0 ‑ 66 MB
Compute Units
NPU
93
| Stage | Time | Memory |
|---|---|---|
First App Load | 25.0 s | 432 MB |
Subsequent App Load | 254 ms | 52‑53 MB |
Inference | 60.4 ms | 0‑66 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device