Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j560vr1n5
Results Ready
Name
bevformer
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[6, 3, 480, 800]
lidar2img: float32[1, 6, 4, 4]
can_bus: float32[18]
use_prev_bev: float32[1]
prev_bev: float32[1, 50, 50, 256]
Completion Time
11/14/2026, 4:36:57 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
1.47 s
Estimated Peak Memory Usage
29 ‑ 63 MB
Compute Units
NPU
1597
StageTimeMemory
First App Load
2.08 min922‑923 MB
Subsequent App Load
389 ms3 MB
Inference
1.47 s29‑63 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