Profile Job Results
Jobs
jp49d70l5
Results Ready
Name
resnet_3d
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
video: uint8[1, 16, 112, 112, 15]Completion Time
7/6/2026, 8:31:46 PM
Versions
- LiteRT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
9.66 s
Estimated Peak Memory Usage
3 ‑ 1 GB
Compute Units
NPU
74
CPU
40
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.91 s | 315‑316 MB |
Subsequent App Load | 519 ms | 6 MB |
Inference | 9.66 s | 3‑1 GB |
| 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device