Profile Job Results
Jobs
j5mzyy8dp
Results Ready
Name
whisper_small_quantized_WhisperSmallEncoderQuantizable
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: uint16[1, 80, 3000]Completion Time
3/14/2026, 9:28:13 AM
Options
--qairt_version 2.42 --max_profiler_iterations 10Versions
- ONNX Runtime: 1.24.1
- QAIRT: v2.42.0.251225135753_193295
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.03.09.0
Estimated Inference Time
241 ms
Estimated Peak Memory Usage
63 ‑ 74 MB
Compute Units
NPU
1774
| Stage | Time | Memory |
|---|---|---|
First App Load | 365 ms | 135‑142 MB |
Subsequent App Load | 330 ms | 131‑138 MB |
Inference | 241 ms | 63‑74 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 |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device