Profile Job Results
Jobs
j56okk905
Results Ready
Name
opus_mt_en_ja_encoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
encoder_attention_mask: int32[1, 256]input_ids: int32[1, 256]Completion Time
10/20/2026, 7:04:03 AM
Options
--qairt_version 2.50Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.10.10.0
Estimated Inference Time
4.56 ms
Estimated Peak Memory Usage
2 ‑ 6 MB
Compute Units
NPU
329
| Stage | Time | Memory |
|---|---|---|
First App Load | 225 ms | 2‑3 MB |
Subsequent App Load | 188 ms | 2‑3 MB |
Inference | 4.56 ms | 2‑6 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







