Profile Job Results
Jobs
jpekwl80p
Results Ready
Name
whisper_large_v3_turbo_float_HfWhisperEncoder
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: float32[1, 128, 3000]Completion Time
10/25/2025, 10:00:05 PM
Options
--qairt_version latest --max_profiler_iterations 10Versions
- QAIRT: v2.39.0.250925215840_163802-auto
- QNN Backend API: 5.39.0
- QNN Core API: 2.29.0
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
2.17 s
Estimated Peak Memory Usage
2 ‑ 10 MB
Compute Units
NPU
5034
| Stage | Time | Memory |
|---|---|---|
First App Load | 7.69 s | 34‑42 MB |
Subsequent App Load | 5.10 s | 44‑52 MB |
Inference | 2.17 s | 2‑10 MB |
| QNN | Value |
|---|---|
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device