Profile Job Results
Jobs
jpx11qylg
Results Ready
Name
distil_bert_base_uncased_hf_w8a16
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_tokens: int32[1, 384]attention_masks: uint16[1, 384]mask_indices: int32[1]Completion Time
2/1/2026, 7:25:15 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
1.35 s
Estimated Peak Memory Usage
182 ‑ 265 MB
Compute Units
CPU
561
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.55 s | 261‑262 MB |
Subsequent App Load | 5.60 s | 264‑265 MB |
Inference | 1.35 s | 182‑265 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device







