Profile Job Results
Jobs
jp2rjkrqg
Results Ready
Name
whisper_large_v3_turbo_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, 128, 3000]Completion Time
9/19/2026, 11:55:52 AM
Options
--qairt_version latest --max_profiler_iterations 10Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
708 ms
Estimated Peak Memory Usage
1 ‑ 34 MB
Compute Units
NPU
5026
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.48 s | 3‑4 MB |
Subsequent App Load | 904 ms | 3‑4 MB |
Inference | 708 ms | 1‑34 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device