Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Electra-Bert-Base-Discrim-Google

Profile Job Results

Jobs
jp2eoy3qp
Results Ready
Name
electra_bert_base_discrim_google
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]
attention_masks: float32[1, 384]
Completion Time
8/8/2026, 4:28:58 PM
Versions
  • Lite RT: 1.4.5
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.07.31.1
Estimated Inference Time
22.2 ms
Estimated Peak Memory Usage
0 ‑ 215 MB
Compute Units
NPU
524
StageTimeMemory
First App Load
14.8 s629‑630 MB
Subsequent App Load
402 ms214‑215 MB
Inference
22.2 ms0‑215 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue

Sign up to run this model on a hosted Qualcomm® device!

Run on device