Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j560rrdv5
Results Ready
Name
parakeet_tdt_decoder
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
h_in: float32[2, 1, 640]
token_id: int32[1, 1]
c_in: float32[2, 1, 640]
Completion Time
11/15/2026, 1:30:36 PM
Options
--qairt_version latest
Versions
  • QAIRT: v2.51.0.260929181845
  • QNN Backend API: 5.51.0
  • QNN Core API: 2.40.0
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
221 μs
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
68
StageTimeMemory
First App Load
3.02 s79‑80 MB
Subsequent App Load
179 ms2‑3 MB
Inference
221 μs0‑3 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