Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp43y3025
Results Ready
Name
pi05_backbone
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.9
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
prefix_att_2d_masks: float32[1, 1, 968, 968]
hidden_state: float32[1, 968, 2048]
rope_emb_cos: float32[1, 968, 1, 128]
rope_emb_sin: float32[1, 968, 1, 128]
Completion Time
8/8/2026, 8:30:12 AM
Versions
  • QAIRT: v2.45.0.260326154327
  • QNN Backend API: 5.45.0
  • QNN Core API: 2.34.0
  • Qualcomm Linux: 1.9-ver.1.0
  • AI Hub: aihub-2026.07.31.1
Estimated Inference Time
399 ms
Estimated Peak Memory Usage
12 ‑ 60 MB
Compute Units
NPU
2473
StageTimeMemory
First App Load
895 ms2 MB
Subsequent App Load
882 ms23 MB
Inference
399 ms12‑60 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].value3.0
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