Profile Job Results
Jobs
jp8mqjj85
Results Ready
Name
whisper_large_v3_turbo_HfWhisperEncoder
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: float16[1, 128, 3000]Completion Time
6/28/2025, 8:40:59 AM
Options
--qairt_version 2.33 --max_profiler_iterations 10Versions
- ONNX Runtime: 1.21.1
- QAIRT: v2.33.2.250410134701_117956
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.06.12.0
Estimated Inference Time
603 ms
Estimated Peak Memory Usage
32 ‑ 47 MB
Compute Units
NPU
5026
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.64 s | 1 GB |
Subsequent App Load | 1.94 s | 1 GB |
Inference | 603 ms | 32‑47 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
Sign up to run this model on a hosted Qualcomm® device!
Run on device