Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp06o429p
Results Ready
Name
nomic_embed_text
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 128]
attention_masks: int32[1, 128]
Completion Time
8/8/2026, 5:37:03 PM
Versions
  • ONNX Runtime: 1.27.1
  • QAIRT: v2.45.0.260326154327
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.07.31.1
Estimated Inference Time
7.98 ms
Estimated Peak Memory Usage
0 ‑ 323 MB
Compute Units
NPU
673
StageTimeMemory
First App Load
8.90 s1 GB
Subsequent App Load
591 ms172‑415 MB
Inference
7.98 ms0‑323 MB
ONNX RuntimeValue
execution_modeSEQUENTIAL
intra_op_num_threads0
inter_op_num_threads0
enable_memory_patternfalse
enable_cpu_memory_arenafalse
graph_optimization_levelENABLE_ALL
QNN Execution ProviderValue
htp_performance_mode"burst"
htp_graph_finalization_optimization_mode"3"
enable_htp_fp16_precision"1"
capture_network_visualizationsfalse
context_priority"normal"
offload_graph_io_quantization"1"

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

Run on device