Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Nomic-Embed-Text

Profile Job Results

Jobs
jg99lqmmg
Results Ready
Name
nomic_embed_text
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.7
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_tokens: int32[1, 128]
attention_masks: int32[1, 128]
Completion Time
5/2/2026, 2:03:00 PM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 1.7-ver.1.1
  • AI Hub: aihub-2026.04.25.0
Estimated Inference Time
10.6 ms
Estimated Peak Memory Usage
0 ‑ 265 MB
Compute Units
NPU
787
StageTimeMemory
First App Load
6.36 s686‑687 MB
Subsequent App Load
323 ms264‑265 MB
Inference
10.6 ms0‑265 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInference
htp_options.useConvHmxtrue

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

Run on device