Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j5wrx4m4p
Results Ready
Name
agpose_backbone
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
category_label: int32[1]
choose: int32[1, 1024]
fps1: int32[1, 512]
fps2: int32[1, 256]
fps3: int32[1, 128]
fps4: int32[1, 64]
pts: float32[1, 1024, 3]
rgb: float32[1, 3, 224, 224]
Completion Time
11/14/2026, 6:20:07 PM
Options
--qairt_version latest
Versions
  • ONNX Runtime: 1.30.0
  • QNN Execution Provider: 2.5.0
  • QAIRT: v2.51.0.260929181845
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
80.1 ms
Estimated Peak Memory Usage
0 ‑ 5 MB
Compute Units
NPU
1326
StageTimeMemory
First App Load
48.4 s497‑498 MB
Subsequent App Load
577 ms73‑74 MB
Inference
80.1 ms0‑5 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"
num_graph_prepare_threads"1"

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

Run on device