Profile Job Results
Jobs
j57xoqyqg
Results Ready
Name
whisper_small_quantized_w8a16_WhisperSmallEncoderQuantizable
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: uint16[1, 80, 3000]Completion Time
12/6/2025, 1:01:51 PM
Options
--qairt_version 2.37 --max_profiler_iterations 10Versions
- ONNX Runtime: 1.23.0
- QAIRT: v2.37.1.250807093845_124904
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2025.11.18.0
Estimated Inference Time
538 ms
Estimated Peak Memory Usage
30 ‑ 33 MB
Compute Units
NPU
1918
| Stage | Time | Memory |
|---|---|---|
First App Load | 738 ms | 145‑146 MB |
Subsequent App Load | 666 ms | 145‑146 MB |
Inference | 538 ms | 30‑33 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 | "0" |
| 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