Profile Job Results
Jobs
jgdv33y6g
Results Ready
Name
melotts_en_T5Encoder_EN
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, 50]encoder_attention_mask: int32[1, 50]Completion Time
2/22/2026, 10:52:35 AM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.24.1
- QAIRT: v2.42.0.251225135753_193295
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.02.14.0
Estimated Inference Time
620 μs
Estimated Peak Memory Usage
0 ‑ 6 MB
Compute Units
NPU
445
| Stage | Time | Memory |
|---|---|---|
First App Load | 196 ms | 10‑17 MB |
Subsequent App Load | 134 ms | 1‑8 MB |
Inference | 620 μs | 0‑6 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device