Profile Job Results
Jobs
jp4y8k21p
Results Ready
Name
distil_bert_base_uncased_hf
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
mask_indices: int32[1]attention_masks: uint16[1, 384]input_tokens: int32[1, 384]Completion Time
9/19/2026, 1:14:17 PM
Options
--qairt_version latestVersions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
5.72 ms
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
216
| Stage | Time | Memory |
|---|---|---|
First App Load | 7.71 s | 432‑433 MB |
Subsequent App Load | 284 ms | 2‑3 MB |
Inference | 5.72 ms | 0‑3 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device







