Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp3r84vmp
Results Ready
Name
whisper_large_v3_turbo_encoder
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_features: float16[1, 128, 3000]
Completion Time
11/14/2026, 2:13:55 PM
Options
--qairt_version latest --max_profiler_iterations 10
Versions
  • ONNX Runtime: 1.30.0
  • QNN Execution Provider: 2.5.0
  • QAIRT: v2.51.0.260929181845
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
705 ms
Estimated Peak Memory Usage
31 ‑ 36 MB
Compute Units
NPU
4950
StageTimeMemory
First App Load
2.23 s2 GB
Subsequent App Load
1.75 s2 GB
Inference
705 ms31‑36 MB
ONNX RuntimeValue
execution_modeSEQUENTIAL
intra_op_num_threads0
inter_op_num_threads0
enable_memory_patternfalse
enable_cpu_memory_arenafalse
graph_optimization_levelENABLE_ALL
QNN Execution ProviderValue
htp_performance_mode"burst"
htp_graph_finalization_optimization_mode"3"
enable_htp_fp16_precision"1"
capture_network_visualizationsfalse
context_priority"normal"
offload_graph_io_quantization"1"
num_graph_prepare_threads"1"

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

Run on device