Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jglqo7xlp
Results Ready
Name
minilm_v2
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[1, 128]
attention_mask: int32[1, 128]
Completion Time
11/15/2026, 12:09:37 PM
Options
--qairt_version latest
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.51.0.260929181845
  • QNN TfLite Delegate: v2.51.0.260929181845
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
1.19 ms
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
279
StageTimeMemory
First App Load
1.22 s174‑176 MB
Subsequent App Load
289 ms0‑140 MB
Inference
1.19 ms0‑3 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