Profile Job Results
Jobs
jpe72kv05
Results Ready
Name
bevdet_decoder
Target Device
- Samsung Galaxy S26
- Android 16
- Snapdragon® 8 Elite Gen 5 for Galaxy | SM8850-AD
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
bev_feature: float32[1, 64, 128, 128]Completion Time
9/19/2026, 1:31:20 PM
Options
--qairt_version latestVersions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Android: 16 (BP4A.251205.006)
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
5.00 ms
Estimated Peak Memory Usage
1 ‑ 148 MB
Compute Units
NPU
52
| Stage | Time | Memory |
|---|---|---|
First App Load | 765 ms | 170‑178 MB |
Subsequent App Load | 136 ms | 38‑187 MB |
Inference | 5.00 ms | 1‑148 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