Profile Job Results
Jobs
jglx3r2lg
Results Ready
Name
whisper_base_encoder
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: float16[1, 80, 3000]Completion Time
8/22/2026, 11:33:52 AM
Options
--max_profiler_iterations 10Versions
- ONNX Runtime: 1.27.1
- QAIRT: v2.45.0.260326154327
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
57.4 ms
Estimated Peak Memory Usage
37 ‑ 41 MB
Compute Units
NPU
556
| Stage | Time | Memory |
|---|---|---|
First App Load | 274 ms | 57‑58 MB |
Subsequent App Load | 263 ms | 57‑58 MB |
Inference | 57.4 ms | 37‑41 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