Profile Job Results
Jobs
j5mwozxqp
Results Ready
Name
whisper_small_quantized_encoder
Target Device
- Dragonwing Q-6690 MTP
- Android 15
- Qualcomm® Dragonwing™ Q-6690 | QCM6690
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: uint16[1, 80, 3000]Completion Time
4/4/2026, 11:11:07 PM
Options
--qairt_version 2.42 --max_profiler_iterations 10Versions
- ONNX Runtime: 1.24.3
- QAIRT: v2.42.0.251225135753_193295
- Android: 15 (AQ3A.250330.001)
- Build ID: QCM6690.LA.1.0.r1-00117-STD.PROD-1
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
4.17 s
Estimated Peak Memory Usage
2 ‑ 13 MB
Compute Units
NPU
2038
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.34 s | 196‑204 MB |
Subsequent App Load | 1.24 s | 181‑192 MB |
Inference | 4.17 s | 2‑13 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 | "0" |
| 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