Profile Job Results
Jobs
jp1orrnl5
Results Ready
Name
opus_mt_en_it_decoder
Target Device
- Snapdragon X Elite CRD
- Windows 11
- Snapdragon® X Elite | SC8380XP
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
block_0_cross_key_states: uint8[1, 8, 256, 64]block_0_cross_value_states: uint8[1, 8, 256, 64]block_1_cross_key_states: uint8[1, 8, 256, 64]block_1_cross_value_states: uint8[1, 8, 256, 64]block_2_cross_key_states: uint8[1, 8, 256, 64]block_2_cross_value_states: uint8[1, 8, 256, 64]block_3_cross_key_states: uint8[1, 8, 256, 64]block_3_cross_value_states: uint8[1, 8, 256, 64]block_4_cross_key_states: uint8[1, 8, 256, 64]block_4_cross_value_states: uint8[1, 8, 256, 64]block_5_cross_key_states: uint8[1, 8, 256, 64]block_5_cross_value_states: uint8[1, 8, 256, 64]encoder_attention_mask: int32[1, 256]input_ids: int32[1, 1]position: int32[1]block_0_past_self_key_states: uint8[1, 8, 255, 64]block_0_past_self_value_states: uint8[1, 8, 255, 64]block_1_past_self_key_states: uint8[1, 8, 255, 64]block_1_past_self_value_states: uint8[1, 8, 255, 64]block_2_past_self_key_states: uint8[1, 8, 255, 64]block_2_past_self_value_states: uint8[1, 8, 255, 64]block_3_past_self_key_states: uint8[1, 8, 255, 64]block_3_past_self_value_states: uint8[1, 8, 255, 64]block_4_past_self_key_states: uint8[1, 8, 255, 64]block_4_past_self_value_states: uint8[1, 8, 255, 64]block_5_past_self_key_states: uint8[1, 8, 255, 64]block_5_past_self_value_states: uint8[1, 8, 255, 64]Completion Time
10/20/2026, 6:46:28 AM
Options
--qairt_version 2.50Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Windows: Windows 11 (26200)
- Build ID: APSS.WP_HA.1.0-09400-SC8380XRELSFNWZA-8
- AI Hub: aihub-2026.10.10.0
Estimated Inference Time
1.64 ms
Estimated Peak Memory Usage
3 MB
Compute Units
NPU
365
| Stage | Time | Memory |
|---|---|---|
First App Load | 391 ms | 10 MB |
Subsequent App Load | 331 ms | 10 MB |
Inference | 1.64 ms | 3 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device