Profile Job Results
Jobs
jp2mmxz65
Results Ready
Name
whisper_large_v3_turbo_float_HfWhisperEncoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.5
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: float16[1, 128, 3000]Completion Time
1/31/2026, 7:15:45 PM
Options
--max_profiler_iterations 10Versions
- QAIRT: v2.42.0.251225135753_193295
- QNN Backend API: 5.41.0
- QNN Core API: 2.32.0
- Qualcomm Linux: 1.5-ver.1.1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
699 ms
Estimated Peak Memory Usage
1 ‑ 32 MB
Compute Units
NPU
5034
| Stage | Time | Memory |
|---|---|---|
First App Load | 780 ms | 6‑7 MB |
Subsequent App Load | 779 ms | 4‑5 MB |
Inference | 699 ms | 1‑32 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 | 2.0 |
| 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