Profile Job Results
Jobs
jgd0vyz6p
Results Ready
Name
whisper_small_quantized_encoder
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: uint16[1, 80, 3000]Completion Time
6/2/2026, 11:47:06 AM
Options
--qairt_version 2.42 --max_profiler_iterations 10Versions
- ONNX Runtime: 1.25.0
- QAIRT: v2.42.0.251225135753_193295
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.05.27.0
Estimated Inference Time
372 ms
Estimated Peak Memory Usage
54 ‑ 57 MB
Compute Units
NPU
2038
| Stage | Time | Memory |
|---|---|---|
First App Load | 895 ms | 134‑136 MB |
Subsequent App Load | 523 ms | 128‑131 MB |
Inference | 372 ms | 54‑57 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