Profile Job Results
Jobs
j5729w0qp
Results Ready
Name
whisper_tiny_en_WhisperDecoder
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[4, 6, 64, 1500]v_cache_cross: float32[4, 6, 1500, 64]k_cache_self: float32[4, 6, 64, 224]v_cache_self: float32[4, 6, 224, 64]Completion Time
3/11/2025, 12:54:06 PM
Versions
- QAIRT: v2.32.0.250228225014_116386-auto
- QNN Backend API: 5.32.0
- QNN Core API: 2.24.0
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
15.2 ms
Estimated Peak Memory Usage
8 ‑ 17 MB
Compute Units
NPU
447
| Stage | Time | Memory |
|---|---|---|
First App Load | 516 ms | 0‑10 MB |
Subsequent App Load | 535 ms | 0‑10 MB |
Inference | 15.2 ms | 8‑17 MB |
| QNN | Value |
|---|---|
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device