Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j560vnzn5
Results Ready
Name
whisper_large_v3_turbo_quantized_encoder
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: uint16[1, 128, 3000]
Completion Time
11/14/2026, 1:11:43 PM
Options
--qairt_version latest --max_profiler_iterations 10
Versions
  • QAIRT: v2.51.0.260929181845
  • QNN Backend API: 5.51.0
  • QNN Core API: 2.40.0
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
271 ms
Estimated Peak Memory Usage
1 ‑ 3 MB
Compute Units
NPU
6314
StageTimeMemory
First App Load
1.60 s4‑5 MB
Subsequent App Load
593 ms0‑11 MB
Inference
271 ms1‑3 MB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.optimizations[0].typeFINALIZE_OPTIMIZATION_FLAG
default_graph_options.htp_options.optimizations[0].value3.0
default_graph_options.htp_options.precisionFLOAT16
default_graph_options.htp_options.vtcm_size0

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

Run on device