Profile Job Results
Jobs
jgnx4w1q5
Results Ready
Name
distil_bert_base_uncased_hf
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]attention_masks: float32[1, 384]mask_indices: int32[1]Completion Time
6/13/2026, 3:55:54 PM
Versions
- LiteRT: 1.4.4
- Android: 14 (UAG2.240908.001)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
- AI Hub: aihub-2026.06.08.2
Estimated Inference Time
180 ms
Estimated Peak Memory Usage
2 ‑ 26 MB
Compute Units
GPU
282
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 22.7 s | 609‑614 MB |
Subsequent App Load | 2.76 s | 493‑519 MB |
Inference | 180 ms | 2‑26 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device





