Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp1646rl5
Results Ready
Name
distil_whisper_encoder
Target Device
  • Samsung Galaxy S26
  • Android 16
  • Snapdragon® 8 Elite Gen 5 for Galaxy | SM8850-AD
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: float32[1, 80, 3000]
Completion Time
7/25/2026, 4:00:35 PM
Options
--compute_unit gpu --max_profiler_iterations 10
Versions
  • Lite RT: 1.4.4
  • Android: 16 (BP4A.251205.006)
  • AI Hub: aihub-2026.07.17.0
Estimated Inference Time
361 ms
Estimated Peak Memory Usage
42 ‑ 81 MB
Compute Units
GPU
1358
CPU
8
StageTimeMemory
First App Load
3.47 s722‑731 MB
Subsequent App Load
382 ms625‑748 MB
Inference
361 ms42‑81 MB
Lite RTValue
number_of_threads4
GPUv2 DelegateValue
inference_preferenceTFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED
inference_priority1TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY
inference_priority2TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE
inference_priority3TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION
XNNPACK DelegateValue

Sign up to run this model on a hosted Qualcomm® device!

Run on device