Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Whisper-Large-V3-Turbo

Profile Job Results

Jobs
j5q2yr475
Results Ready
Name
whisper_large_v3_turbo_HfWhisperDecoder
Target Device
  • Snapdragon X2 Elite CRD
  • Windows 11
  • Snapdragon® X2 Elite | SC8480XP
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 1]
attention_mask: float16[1, 1, 1, 200]
k_cache_self_0_in: float16[20, 1, 64, 199]
v_cache_self_0_in: float16[20, 1, 199, 64]
k_cache_self_1_in: float16[20, 1, 64, 199]
v_cache_self_1_in: float16[20, 1, 199, 64]
k_cache_self_2_in: float16[20, 1, 64, 199]
v_cache_self_2_in: float16[20, 1, 199, 64]
k_cache_self_3_in: float16[20, 1, 64, 199]
v_cache_self_3_in: float16[20, 1, 199, 64]
k_cache_cross_0: float16[20, 1, 64, 1500]
v_cache_cross_0: float16[20, 1, 1500, 64]
k_cache_cross_1: float16[20, 1, 64, 1500]
v_cache_cross_1: float16[20, 1, 1500, 64]
k_cache_cross_2: float16[20, 1, 64, 1500]
v_cache_cross_2: float16[20, 1, 1500, 64]
k_cache_cross_3: float16[20, 1, 64, 1500]
v_cache_cross_3: float16[20, 1, 1500, 64]
position_ids: int32[1]
Completion Time
2/21/2026, 9:29:49 AM
Options
--qairt_version 2.42
Versions
  • ONNX Runtime: 1.24.1
  • QAIRT: v2.42.0.251225135753_193295
  • Windows: Windows 11 (28000)
  • Build ID: APSS.WP_GL.1.0.c4-04500-SC8480XRELCSP4ZA-5
  • AI Hub: aihub-2026.02.14.0
Estimated Inference Time
4.45 ms
Estimated Peak Memory Usage
399 MB
Compute Units
NPU
1222
StageTimeMemory
First App Load
825 ms458 MB
Subsequent App Load
698 ms458 MB
Inference
4.45 ms399 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"

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

Run on device