Profile Job Results
Jobs
jp0ry629p
Results Ready
Name
melotts_zh_BertWrapper_ZH
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 200]attention_mask: int32[1, 200]token_type_ids: int32[1, 200]Completion Time
3/8/2026, 7:43:11 PM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.24.1
- QAIRT: v2.42.0.251225135753_193295
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.02.26.0
Estimated Inference Time
8.89 ms
Estimated Peak Memory Usage
1 ‑ 4 MB
Compute Units
NPU
343
| Stage | Time | Memory |
|---|---|---|
First App Load | 323 ms | 305 MB |
Subsequent App Load | 345 ms | 303‑304 MB |
Inference | 8.89 ms | 1‑4 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 | "2" |
| 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