Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpr79e3kg
Results Ready
Name
whisper_large_v3_turbo_quantized_decoder
Target Device
  • Dragonwing RB3 Gen 2 Vision Kit
  • Qualcomm Linux 1.6
  • Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[1, 1]
attention_mask: uint16[1, 1, 1, 200]
k_cache_self_0_in: uint8[20, 1, 64, 199]
v_cache_self_0_in: uint8[20, 1, 199, 64]
k_cache_self_1_in: uint8[20, 1, 64, 199]
v_cache_self_1_in: uint8[20, 1, 199, 64]
k_cache_self_2_in: uint8[20, 1, 64, 199]
v_cache_self_2_in: uint8[20, 1, 199, 64]
k_cache_self_3_in: uint8[20, 1, 64, 199]
v_cache_self_3_in: uint8[20, 1, 199, 64]
k_cache_cross_0: uint8[20, 1, 64, 1500]
v_cache_cross_0: uint8[20, 1, 1500, 64]
k_cache_cross_1: uint8[20, 1, 64, 1500]
v_cache_cross_1: uint8[20, 1, 1500, 64]
k_cache_cross_2: uint8[20, 1, 64, 1500]
v_cache_cross_2: uint8[20, 1, 1500, 64]
k_cache_cross_3: uint8[20, 1, 64, 1500]
v_cache_cross_3: uint8[20, 1, 1500, 64]
position_ids: int32[1]
Completion Time
11/14/2026, 12:53:15 PM
Options
--qairt_version latest
Versions
  • ONNX Runtime: 1.30.0
  • QNN Execution Provider: 2.5.0
  • QAIRT: v2.51.0.260929181845
  • Qualcomm Linux: 1.6-ver.1.2
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
19.0 ms
Estimated Peak Memory Usage
15 ‑ 34 MB
Compute Units
NPU
1533
StageTimeMemory
First App Load
472 ms296‑297 MB
Subsequent App Load
447 ms294‑295 MB
Inference
19.0 ms15‑34 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"0"
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