Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp1vwwwkp
Results Ready
Name
electra_bert_base_discrim_google
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.7
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 384]
attention_masks: float32[1, 384]
Completion Time
7/5/2026, 8:11:50 AM
Versions
  • LiteRT: 1.4.4
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 1.7-ver.1.1
  • AI Hub: aihub-2026.06.19.2
Estimated Inference Time
21.4 ms
Estimated Peak Memory Usage
0 ‑ 214 MB
Compute Units
NPU
524
StageTimeMemory
First App Load
11.5 s590 MB
Subsequent App Load
309 ms214‑215 MB
Inference
21.4 ms0‑214 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