Profile Job Results
Jobs
jgk3qd0w5
Results Ready
Name
yolov7_w8a8
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 640, 640, 3]Completion Time
10/25/2025, 1:15:29 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
69.2 ms
Estimated Peak Memory Usage
15 ‑ 43 MB
Compute Units
GPU
146
CPU
71
| Stage | Time | Memory |
|---|---|---|
First App Load | 15.1 s | 118‑129 MB |
Subsequent App Load | 15.0 s | 109‑139 MB |
Inference | 69.2 ms | 15‑43 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