Profile Job Results
Jobs
jp8xl4y8g
Results Ready
Name
distil_bert_base_uncased_hf
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.9
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]attention_masks: uint16[1, 384]mask_indices: int32[1]Completion Time
9/5/2026, 9:30:23 AM
Versions
- ONNX Runtime: 1.27.1
- QAIRT: v2.45.0.260326154327
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
8.41 ms
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
255
| Stage | Time | Memory |
|---|---|---|
First App Load | 10.5 s | 730‑731 MB |
Subsequent App Load | 406 ms | 122‑123 MB |
Inference | 8.41 ms | 0‑3 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