Profile Job Results
Jobs
jp4ww22vg
Results Ready
Name
electra_bert_base_discrim_google_float
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.5
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_tokens: int32[1, 384]attention_masks: float32[1, 384]Completion Time
2/1/2026, 7:59:26 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.42.0.251225135753_193295
- QNN TfLite Delegate: v2.42.0.251225135753_193295
- Qualcomm Linux: 1.5-ver.1.1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
22.4 ms
Estimated Peak Memory Usage
0 ‑ 214 MB
Compute Units
NPU
526
| Stage | Time | Memory |
|---|---|---|
First App Load | 8.38 s | 1 GB |
Subsequent App Load | 269 ms | 213‑214 MB |
Inference | 22.4 ms | 0‑214 MB |
| TensorFlow Lite | 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 | kHtpOptimizeForInference |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device