Profile Job Results
Jobs
jpyj18mrp
Results Ready
Name
whisper_medium_en_WhisperDecoderInf
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[24, 16, 64, 1500]v_cache_cross: float32[24, 16, 1500, 64]k_cache_self: float32[24, 16, 64, 224]v_cache_self: float32[24, 16, 224, 64]Completion Time
6/28/2025, 8:14:30 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.34.2.250528164111_119506
- QNN TfLite Delegate: v2.34.2.250528164111_119506
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.06.12.0
Estimated Inference Time
91.2 ms
Estimated Peak Memory Usage
0 ‑ 2 GB
Compute Units
NPU
6377
| Stage | Time | Memory |
|---|---|---|
First App Load | 57.9 s | 906‑914 MB |
Subsequent App Load | 58.2 s | 1‑3 GB |
Inference | 91.2 ms | 0‑2 GB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device