Profile Job Results
Jobs
jp297v34g
Results Ready
Name
huggingface_wavlm_base_plus
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input: float32[1, 160000]Completion Time
7/26/2025, 7:32:45 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.34.2.250528164111_119506
- QNN TfLite Delegate: v2.34.2.250528164111_119506
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
260 ms
Estimated Peak Memory Usage
0 ‑ 55 MB
Compute Units
NPU
873
| Stage | Time | Memory |
|---|---|---|
First App Load | 26.8 s | 2 GB |
Subsequent App Load | 30.0 s | 2 GB |
Inference | 260 ms | 0‑55 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