Profile Job Results
Jobs
jgnev03mg
Results Ready
Name
hrnet_pose_w8a8
Target Device
- RB5 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 256, 192, 3]Completion Time
1/11/2026, 2:11:55 AM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
61.1 ms
Estimated Peak Memory Usage
0 ‑ 181 MB
Compute Units
GPU
518
| Stage | Time | Memory |
|---|---|---|
First App Load | 8.59 s | 336‑338 MB |
Subsequent App Load | 381 ms | 224‑227 MB |
Inference | 61.1 ms | 0‑181 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
Sign up to run this model on a hosted Qualcomm® device!
Run on device