Profile Job Results
Jobs
jgl2x6n8p
Results Ready
Name
whisper_tiny_en_HfWhisperDecoder
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 1]attention_mask: float32[1, 1, 1, 200]k_cache_self_0_in: float32[6, 1, 64, 199]v_cache_self_0_in: float32[6, 1, 199, 64]k_cache_self_1_in: float32[6, 1, 64, 199]v_cache_self_1_in: float32[6, 1, 199, 64]k_cache_self_2_in: float32[6, 1, 64, 199]v_cache_self_2_in: float32[6, 1, 199, 64]k_cache_self_3_in: float32[6, 1, 64, 199]v_cache_self_3_in: float32[6, 1, 199, 64]k_cache_cross_0: float32[6, 1, 64, 1500]v_cache_cross_0: float32[6, 1, 1500, 64]k_cache_cross_1: float32[6, 1, 64, 1500]v_cache_cross_1: float32[6, 1, 1500, 64]k_cache_cross_2: float32[6, 1, 64, 1500]v_cache_cross_2: float32[6, 1, 1500, 64]k_cache_cross_3: float32[6, 1, 64, 1500]v_cache_cross_3: float32[6, 1, 1500, 64]position_ids: int32[1]Completion Time
8/23/2025, 7:09:16 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.37.0.250724175447_124859
- QNN TfLite Delegate: v2.37.0.250724175447_124859
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.08.21.0
Estimated Inference Time
2.33 ms
Estimated Peak Memory Usage
0 ‑ 111 MB
Compute Units
NPU
624
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.17 s | 530‑537 MB |
Subsequent App Load | 2.22 s | 561‑824 MB |
Inference | 2.33 ms | 0‑111 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