Profile Job Results
Jobs
jp0xk27np
Results Ready
Name
whisper_large_v3_turbo_quantized_encoder
Target Device
- Snapdragon 7 Gen 4 QRD
- Android 15
- Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: uint16[1, 128, 3000]Completion Time
11/14/2026, 12:48:27 PM
Options
--qairt_version latest --max_profiler_iterations 10Versions
- ONNX Runtime: 1.30.0
- QNN Execution Provider: 2.5.0
- QAIRT: v2.51.0.260929181845
- Android: 15 (AQ3A.250411.001)
- Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
- AI Hub: aihub-2026.11.06.1
Estimated Inference Time
488 ms
Estimated Peak Memory Usage
17 ‑ 29 MB
Compute Units
NPU
6314
| Stage | Time | Memory |
|---|---|---|
First App Load | 883 ms | 689‑695 MB |
Subsequent App Load | 816 ms | 672‑683 MB |
Inference | 488 ms | 17‑29 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" |
| num_graph_prepare_threads | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device







