Profile Job Results
Jobs
jp4v0yd1p
Results Ready
Name
yolov6_float
Target Device
- QCS8450 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 640, 640, 3]Completion Time
1/10/2026, 3:12:13 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
22.2 ms
Estimated Peak Memory Usage
6 ‑ 184 MB
Compute Units
GPU
122
CPU
33
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.87 s | 208‑216 MB |
Subsequent App Load | 147 ms | 51‑235 MB |
Inference | 22.2 ms | 6‑184 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device