Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp1m3d27p
Results Ready
Name
whisper_large_v3_turbo_decoder
Target Device
  • Snapdragon 8 Elite Gen 6 QRD
  • Android 17
  • Snapdragon® 8 Elite Gen 6 | SM8950
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[1, 1]
position_ids: int32[1]
k_cache_self_0_in: float16[20, 1, 64, 199]
attention_mask: float16[1, 1, 1, 200]
v_cache_self_0_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_self_1_in: float16[20, 1, 64, 199]
v_cache_self_1_in: float16[20, 1, 199, 64]
k_cache_cross_1: float16[20, 1, 64, 1500]
v_cache_cross_1: float16[20, 1, 1500, 64]
k_cache_self_2_in: float16[20, 1, 64, 199]
v_cache_self_2_in: float16[20, 1, 199, 64]
k_cache_cross_2: float16[20, 1, 64, 1500]
v_cache_cross_2: float16[20, 1, 1500, 64]
k_cache_self_3_in: float16[20, 1, 64, 199]
v_cache_self_3_in: float16[20, 1, 199, 64]
k_cache_cross_3: float16[20, 1, 64, 1500]
v_cache_cross_3: float16[20, 1, 1500, 64]
Completion Time
11/14/2026, 2:11:56 PM
Options
--qairt_version latest
Versions
  • ONNX Runtime: 1.30.0
  • QNN Execution Provider: 2.5.0
  • QAIRT: v2.51.0.260929181845
  • Android: 17 (CQ2A.260820.002-CP2A.260605.016)
  • Build ID: Maili.LA.1.0.r1-00252-STD.PROD-1
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
6.42 ms
Estimated Peak Memory Usage
42 ‑ 48 MB
Compute Units
NPU
1235
StageTimeMemory
First App Load
209 ms440‑450 MB
Subsequent App Load
194 ms433‑440 MB
Inference
6.42 ms42‑48 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