Profile Job Results
Jobs
jp1d01n7p
Results Ready
Name
distil_whisper_encoder
Target Device
- QCS8450 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: float32[1, 80, 3000]Completion Time
4/25/2026, 4:53:20 PM
Options
--compute_unit gpu --max_profiler_iterations 10Versions
- LiteRT: 1.4.2
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.04.13.0
Estimated Inference Time
850 ms
Estimated Peak Memory Usage
40 ‑ 192 MB
Compute Units
GPU
1358
CPU
8
| Stage | Time | Memory |
|---|---|---|
First App Load | 8.60 s | 900‑909 MB |
Subsequent App Load | 807 ms | 481‑714 MB |
Inference | 850 ms | 40‑192 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