Profile Job Results
Jobs
jpek3x2vp
Results Ready
Name
whisper_large_v3_turbo_float_HfWhisperEncoder
Target Device
- SA8255 (Proxy)
- Android 13
- Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: float16[1, 128, 3000]Completion Time
1/10/2026, 5:22:52 PM
Options
--qairt_version latest --max_profiler_iterations 10Versions
- QAIRT: v2.41.0.251128145156_191518
- QNN Backend API: 5.41.0
- QNN Core API: 2.31.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
588 ms
Estimated Peak Memory Usage
1 ‑ 4 MB
Compute Units
NPU
5034
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.69 s | 22‑23 MB |
Subsequent App Load | 1.49 s | 1‑3 MB |
Inference | 588 ms | 1‑4 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| 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