Profile Job Results
Jobs
j57xl6drg
Results Ready
Name
yolox_w8a8
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 640, 640, 3]Completion Time
10/25/2025, 4:11:20 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
102 ms
Estimated Peak Memory Usage
8 ‑ 41 MB
Compute Units
GPU
320
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 25.6 s | 187‑198 MB |
Subsequent App Load | 26.3 s | 185‑221 MB |
Inference | 102 ms | 8‑41 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