Profile Job Results
Jobs
j5ml4ov7g
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: float32[1, 384]mask_indices: int32[1]Completion Time
11/14/2026, 4:45:35 PM
Options
--qairt_version latestVersions
- Lite RT: 1.4.2
- QAIRT: v2.51.0.260929181845
- QNN TfLite Delegate: v2.51.0.260929181845
- Qualcomm Linux: 1.9-ver.1.0
- AI Hub: aihub-2026.11.06.1
Estimated Inference Time
13.9 ms
Estimated Peak Memory Usage
0 ‑ 177 MB
Compute Units
NPU
285
| Stage | Time | Memory |
|---|---|---|
First App Load | 7.13 s | 412‑413 MB |
Subsequent App Load | 320 ms | 177‑178 MB |
Inference | 13.9 ms | 0‑177 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device







