Profile Job Results
Jobs
j5q2y30n5
Results Ready
Name
whisper_small_HfWhisperEncoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: float16[1, 80, 3000]Completion Time
2/22/2026, 3:17:35 PM
Options
--qairt_version 2.42 --max_profiler_iterations 10Versions
- ONNX Runtime: 1.24.1
- QAIRT: v2.42.0.251225135753_193295
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.02.14.0
Estimated Inference Time
137 ms
Estimated Peak Memory Usage
128 ‑ 131 MB
Compute Units
NPU
1606
| Stage | Time | Memory |
|---|---|---|
First App Load | 344 ms | 211‑212 MB |
Subsequent App Load | 382 ms | 211‑212 MB |
Inference | 137 ms | 128‑131 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 | "2" |
| 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