Profile Job Results
Jobs
jp2eoydxp
Results Ready
Name
distil_whisper_encoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: float32[1, 80, 3000]Completion Time
8/8/2026, 5:20:18 PM
Options
--compute_unit gpu --max_profiler_iterations 10Versions
- Lite RT: 1.4.5
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
1.30 s
Estimated Peak Memory Usage
0 ‑ 39 MB
Compute Units
GPU
1358
CPU
8
| Stage | Time | Memory |
|---|---|---|
First App Load | 10.4 s | 802‑803 MB |
Subsequent App Load | 620 ms | 717‑719 MB |
Inference | 1.30 s | 0‑39 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