Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp312v3mg
Results Ready
Name
whisper_small_quantized_w8a16_WhisperSmallDecoderQuantizable
Target Device
  • Samsung Galaxy S24
  • Android 14
  • Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 1]
position_ids: int32[1]
k_cache_self_0_in: uint8[12, 1, 64, 199]
v_cache_self_0_in: uint8[12, 1, 199, 64]
k_cache_cross_0: uint8[12, 1, 64, 1500]
v_cache_cross_0: uint8[12, 1, 1500, 64]
k_cache_self_1_in: uint8[12, 1, 64, 199]
v_cache_self_1_in: uint8[12, 1, 199, 64]
k_cache_cross_1: uint8[12, 1, 64, 1500]
v_cache_cross_1: uint8[12, 1, 1500, 64]
k_cache_self_2_in: uint8[12, 1, 64, 199]
v_cache_self_2_in: uint8[12, 1, 199, 64]
k_cache_cross_2: uint8[12, 1, 64, 1500]
v_cache_cross_2: uint8[12, 1, 1500, 64]
k_cache_self_3_in: uint8[12, 1, 64, 199]
v_cache_self_3_in: uint8[12, 1, 199, 64]
k_cache_cross_3: uint8[12, 1, 64, 1500]
v_cache_cross_3: uint8[12, 1, 1500, 64]
k_cache_self_4_in: uint8[12, 1, 64, 199]
v_cache_self_4_in: uint8[12, 1, 199, 64]
k_cache_cross_4: uint8[12, 1, 64, 1500]
v_cache_cross_4: uint8[12, 1, 1500, 64]
k_cache_self_5_in: uint8[12, 1, 64, 199]
v_cache_self_5_in: uint8[12, 1, 199, 64]
k_cache_cross_5: uint8[12, 1, 64, 1500]
v_cache_cross_5: uint8[12, 1, 1500, 64]
k_cache_self_6_in: uint8[12, 1, 64, 199]
v_cache_self_6_in: uint8[12, 1, 199, 64]
k_cache_cross_6: uint8[12, 1, 64, 1500]
v_cache_cross_6: uint8[12, 1, 1500, 64]
k_cache_self_7_in: uint8[12, 1, 64, 199]
v_cache_self_7_in: uint8[12, 1, 199, 64]
k_cache_cross_7: uint8[12, 1, 64, 1500]
v_cache_cross_7: uint8[12, 1, 1500, 64]
k_cache_self_8_in: uint8[12, 1, 64, 199]
v_cache_self_8_in: uint8[12, 1, 199, 64]
k_cache_cross_8: uint8[12, 1, 64, 1500]
v_cache_cross_8: uint8[12, 1, 1500, 64]
k_cache_self_9_in: uint8[12, 1, 64, 199]
v_cache_self_9_in: uint8[12, 1, 199, 64]
k_cache_cross_9: uint8[12, 1, 64, 1500]
v_cache_cross_9: uint8[12, 1, 1500, 64]
k_cache_self_10_in: uint8[12, 1, 64, 199]
v_cache_self_10_in: uint8[12, 1, 199, 64]
k_cache_cross_10: uint8[12, 1, 64, 1500]
v_cache_cross_10: uint8[12, 1, 1500, 64]
k_cache_self_11_in: uint8[12, 1, 64, 199]
v_cache_self_11_in: uint8[12, 1, 199, 64]
k_cache_cross_11: uint8[12, 1, 64, 1500]
v_cache_cross_11: uint8[12, 1, 1500, 64]
attention_mask: uint16[1, 1, 1, 200]
Completion Time
10/4/2025, 1:19:43 PM
Versions
  • QAIRT: v2.38.0.250901140452_125126
  • QNN Backend API: 5.38.0
  • QNN Core API: 2.28.1
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2025.09.26.0
Estimated Inference Time
6.39 ms
Estimated Peak Memory Usage
30 ‑ 48 MB
Compute Units
NPU
2878
StageTimeMemory
First App Load
192 ms1‑8 MB
Subsequent App Load
185 ms1‑13 MB
Inference
6.39 ms30‑48 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