Profile Job Results
Jobs
jpy608k45
Results Ready
Name
yamnet_w8a8
Target Device
- RB5 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: uint8[1, 1, 96, 64]Completion Time
1/10/2026, 5:25:35 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
1.67 ms
Estimated Peak Memory Usage
0 ‑ 25 MB
Compute Units
GPU
32
| Stage | Time | Memory |
|---|---|---|
First App Load | 652 ms | 43‑45 MB |
Subsequent App Load | 80.0 ms | 31‑33 MB |
Inference | 1.67 ms | 0‑25 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