Profile Job Results
Jobs
jp1w4oolg
Results Ready
Name
whisper_base_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[6, 8, 64, 1500]v_cache_cross
: float32[6, 8, 1500, 64]k_cache_self
: float32[6, 8, 64, 224]v_cache_self
: float32[6, 8, 224, 64]Completion Time
6/28/2025, 8:43:29 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
7.41 ms
Estimated Peak Memory Usage
5 ‑ 148 MB
Compute Units
NPU
983
Stage | Time | Memory |
---|---|---|
First App Load | 4.80 s | 508‑515 MB |
Subsequent App Load | 5.10 s | 489‑720 MB |
Inference | 7.41 ms | 5‑148 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