Profile Job Results
Jobs
jp81jyez5
Results Ready
Name
distil_whisper_encoder
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: float32[1, 80, 3000]Completion Time
8/8/2026, 4:35:19 PM
Options
--compute_unit gpu --max_profiler_iterations 10Versions
- Lite RT: 1.4.5
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
480 ms
Estimated Peak Memory Usage
42 ‑ 188 MB
Compute Units
GPU
1358
CPU
8
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.89 s | 739‑745 MB |
Subsequent App Load | 569 ms | 488‑716 MB |
Inference | 480 ms | 42‑188 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device