Profile Job Results
Jobs
jp4ww848g
Results Ready
Name
opus_mt_en_zh_float_OpusMTEncoder
Target Device
- SA8295P ADP
- Android 14
- Qualcomm® SA8295P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 256]encoder_attention_mask: int32[1, 256]Completion Time
1/31/2026, 11:50:27 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.42.0.251225135753_193295
- QNN TfLite Delegate: v2.42.0.251225135753_193295
- Android: 14 (UQ1A.240205.002)
- Build ID: SA8295P.HQX.4.5.6.0-00006-STD.PROD-1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
5.51 ms
Estimated Peak Memory Usage
6 ‑ 97 MB
Compute Units
NPU
332
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.30 s | 1 GB |
Subsequent App Load | 297 ms | 81‑173 MB |
Inference | 5.51 ms | 6‑97 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device