Profile Job Results
Jobs
jp0oy0v2p
Results Ready
Name
mediapipe_pose_pose_detector
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 128, 128, 3]Completion Time
10/20/2026, 8:17:29 AM
Options
--qairt_version 2.50Versions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.10.10.0
Estimated Inference Time
520 μs
Estimated Peak Memory Usage
0 ‑ 4 MB
Compute Units
NPU
113
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.32 s | 47‑48 MB |
Subsequent App Load | 200 ms | 4‑5 MB |
Inference | 520 μs | 0‑4 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