Profile Job Results
Jobs
j57or2erg
Results Ready
Name
whisper_small_quantized_encoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: uint16[1, 80, 3000]Completion Time
10/3/2026, 2:25:36 PM
Options
--max_profiler_iterations 10Versions
- ONNX Runtime: 1.30.0
- QAIRT: v2.50.0.260828221209
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
58.8 ms
Estimated Peak Memory Usage
63 ‑ 67 MB
Compute Units
NPU
1894
| Stage | Time | Memory |
|---|---|---|
First App Load | 338 ms | 123 MB |
Subsequent App Load | 338 ms | 123‑124 MB |
Inference | 58.8 ms | 63‑67 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