Profile Job Results

Jobs
jp4jl382p
Results Ready
Name
mobile_bert_uncased_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]
mask_indices: int32[1]
Completion Time
5/2/2026, 8:36:54 AM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 1.7-ver.1.1
  • AI Hub: aihub-2026.04.25.0
Estimated Inference Time
27.9 ms
Estimated Peak Memory Usage
0 ‑ 82 MB
Compute Units
NPU
1079
StageTimeMemory
First App Load
6.64 s295 MB
Subsequent App Load
279 ms83‑85 MB
Inference
27.9 ms0‑82 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInference
htp_options.useConvHmxtrue

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

Run on device