Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgkk6o9og
Results Ready
Name
qwen3_vl_8b_instruct_vision_encoder_qwen3_vl_8b_instruct
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.9
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
pixel_values: uint16[1024, 1536]
position_ids_cos: uint16[1024, 36]
position_ids_sin: uint16[1024, 36]
window_attention_mask: float16[1, 1024, 1024]
full_attention_mask: uint16[1, 1024, 1024]
Completion Time
11/17/2026, 3:57:05 AM
Options
--qairt_version latest
Versions
  • QAIRT: v2.51.0.260929181845
  • QNN Backend API: 5.51.0
  • QNN Core API: 2.40.0
  • Qualcomm Linux: 1.9-ver.1.0
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
242 ms
Estimated Peak Memory Usage
7 ‑ 25 MB
Compute Units
NPU
1652
StageTimeMemory
First App Load
522 ms2‑3 MB
Subsequent App Load
501 ms4‑5 MB
Inference
242 ms7‑25 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