Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpv903rj5
Results Ready
Name
pi05_token_emb
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
lang_tokens: int32[1, 200]
img_embed1: float32[1, 256, 2048]
img_embed2: float32[1, 256, 2048]
img_embed3: float32[1, 256, 2048]
lang_mask: float32[1, 200]
Completion Time
7/4/2026, 8:59:05 AM
Versions
  • QAIRT: v2.45.0.260326154327
  • QNN Backend API: 5.45.0
  • QNN Core API: 2.34.0
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.06.19.2
Estimated Inference Time
3.55 ms
Estimated Peak Memory Usage
2 ‑ 3 MB
Compute Units
NPU
34
StageTimeMemory
First App Load
1.65 s2‑3 MB
Subsequent App Load
497 ms0‑15 MB
Inference
3.55 ms2‑3 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