Profile Job Results
Jobs
jgn36edq5
Results Ready
Name
whisper_base_float_HfWhisperEncoder
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: float16[1, 80, 3000]Completion Time
10/14/2025, 12:36:57 PM
Options
--max_profiler_iterations 10Versions
- QAIRT: v2.38.0.250901140452_125126
- QNN Backend API: 5.38.0
- QNN Core API: 2.28.1
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.10.03.0
Estimated Inference Time
112 ms
Estimated Peak Memory Usage
1 ‑ 21 MB
Compute Units
NPU
568
| Stage | Time | Memory |
|---|---|---|
First App Load | 237 ms | 18‑27 MB |
Subsequent App Load | 248 ms | 1‑9 MB |
Inference | 112 ms | 1‑21 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