Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Albert-Base-V2-Hf

Profile Job Results

Jobs
jp2j1wxm5
Results Ready
Name
albert_base_v2_hf
Target Device
  • Samsung Galaxy S22 5G
  • Android 12
  • Snapdragon® 8 Gen 1 | SM8450
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
6/13/2026, 11:23:52 AM
Versions
  • LiteRT: 1.4.4
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2026.06.08.2
Estimated Inference Time
34.4 ms
Estimated Peak Memory Usage
0 ‑ 427 MB
Compute Units
NPU
538
StageTimeMemory
First App Load
7.54 s363‑372 MB
Subsequent App Load
254 ms32‑460 MB
Inference
34.4 ms0‑427 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