Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
GKT

Profile Job Results

Jobs
jp487311g
Results Ready
Name
gkt
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.7
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 6, 3, 224, 480]
intrinsics: float32[1, 6, 3, 3]
extrinsics: float32[1, 6, 4, 4]
inv_intrinsics: float32[1, 6, 3, 3]
inv_extrinsics: float32[1, 6, 4, 4]
Completion Time
6/13/2026, 10:56:53 AM
Versions
  • ONNX Runtime: 1.25.0
  • QAIRT: v2.45.0.260326154327
  • Qualcomm Linux: 1.7-ver.1.1
  • AI Hub: aihub-2026.06.08.2
Estimated Inference Time
110 ms
Estimated Peak Memory Usage
7 ‑ 10 MB
Compute Units
NPU
537
StageTimeMemory
First App Load
320 ms22‑23 MB
Subsequent App Load
300 ms20‑21 MB
Inference
110 ms7‑10 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"2"
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