Profile Job Results
Jobs
jg9jlwvm5
Results Ready
Name
whisper_medium_en_WhisperDecoderInf
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
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
4/8/2025, 9:29:27 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 15 (AQ3A.241126.002)
- Build ID: Pakala.LA.1.0.r1-01152-STD.PROD-1
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
74.3 ms
Estimated Peak Memory Usage
42 ‑ 928 MB
Compute Units
NPU
6377
| Stage | Time | Memory |
|---|---|---|
First App Load | 30.0 s | 1 GB |
Subsequent App Load | 31.1 s | 1‑2 GB |
Inference | 74.3 ms | 42‑928 MB |
| 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