Profile Job Results

Jobs
jp2mm19q5
Results Ready
Name
distil_bert_base_uncased_hf_w8a16
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.5
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
attention_masks: uint16[1, 384]
input_tokens: int32[1, 384]
mask_indices: int32[1]
Completion Time
2/1/2026, 8:31:46 AM
Versions
  • QAIRT: v2.42.0.251225135753_193295
  • QNN Backend API: 5.41.0
  • QNN Core API: 2.32.0
  • Qualcomm Linux: 1.5-ver.1.1
  • AI Hub: aihub-2026.01.22.0
Estimated Inference Time
9.25 ms
Estimated Peak Memory Usage
2 ‑ 4 MB
Compute Units
NPU
221
StageTimeMemory
First App Load
5.60 s597‑598 MB
Subsequent App Load
188 ms1‑2 MB
Inference
9.25 ms2‑4 MB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.optimizations[0].typeFINALIZE_OPTIMIZATION_FLAG
default_graph_options.htp_options.optimizations[0].value2.0
default_graph_options.htp_options.precisionFLOAT16
default_graph_options.htp_options.vtcm_size0

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

Run on device