Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j560v4865
Results Ready
Name
opus_mt_en_ja_decoder
Target Device
  • Snapdragon 8 Elite Extreme Gen 6 QRD
  • Android 17
  • Snapdragon® 8 Elite Extreme Gen 6 | SM8975
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
block_5_cross_key_states: float32[1, 8, 256, 64]
block_4_cross_key_states: float32[1, 8, 256, 64]
block_3_cross_key_states: float32[1, 8, 256, 64]
block_2_cross_key_states: float32[1, 8, 256, 64]
block_1_cross_key_states: float32[1, 8, 256, 64]
block_0_cross_key_states: float32[1, 8, 256, 64]
position: int32[1]
input_ids: int32[1, 1]
block_0_past_self_key_states: float32[1, 8, 255, 64]
block_0_past_self_value_states: float32[1, 8, 255, 64]
encoder_attention_mask: int32[1, 256]
block_0_cross_value_states: float32[1, 8, 256, 64]
block_1_past_self_key_states: float32[1, 8, 255, 64]
block_1_past_self_value_states: float32[1, 8, 255, 64]
block_1_cross_value_states: float32[1, 8, 256, 64]
block_2_past_self_key_states: float32[1, 8, 255, 64]
block_2_past_self_value_states: float32[1, 8, 255, 64]
block_2_cross_value_states: float32[1, 8, 256, 64]
block_3_past_self_key_states: float32[1, 8, 255, 64]
block_3_past_self_value_states: float32[1, 8, 255, 64]
block_3_cross_value_states: float32[1, 8, 256, 64]
block_4_past_self_key_states: float32[1, 8, 255, 64]
block_4_past_self_value_states: float32[1, 8, 255, 64]
block_4_cross_value_states: float32[1, 8, 256, 64]
block_5_past_self_key_states: float32[1, 8, 255, 64]
block_5_past_self_value_states: float32[1, 8, 255, 64]
block_5_cross_value_states: float32[1, 8, 256, 64]
Completion Time
11/14/2026, 7:56:23 AM
Options
--qairt_version latest
Versions
  • QAIRT: v2.51.0.260929181845
  • QNN Backend API: 5.51.0
  • QNN Core API: 2.40.0
  • Android: 17 (CQ2A.260820.002-CP2A.260605.016)
  • Build ID: Hawi.LA.1.0.r1-01035-STD.PROD-1
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
1.86 ms
Estimated Peak Memory Usage
1 ‑ 11 MB
Compute Units
NPU
254
StageTimeMemory
First App Load
118 ms1‑8 MB
Subsequent App Load
117 ms1‑12 MB
Inference
1.86 ms1‑11 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
default_graph_options.htp_options.enable_precision_compensationtrue

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

Run on device