Profile Job Results
Jobs
jgk32xk25
Results Ready
Name
yamnet_w8a8
Target Device
- QCS8450 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: uint8[1, 1, 96, 64]Completion Time
11/29/2025, 5:53:42 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.40.0.251030114326_189385
- QNN TfLite Delegate: v2.40.0.251030114326_189385
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.11.18.0
Estimated Inference Time
204 μs
Estimated Peak Memory Usage
0 ‑ 30 MB
Compute Units
NPU
32
| Stage | Time | Memory |
|---|---|---|
First App Load | 470 ms | 113‑122 MB |
Subsequent App Load | 452 ms | 134‑270 MB |
Inference | 204 μs | 0‑30 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device