Profile Job Results
Jobs
jp2ozvj4g
Results Ready
Name
qwen3_vl_4b_instruct_vision_encoder_qwen3_vl_4b_instruct
Target Device
- Snapdragon X2 Elite CRD
- Windows 11
- Snapdragon® X2 Elite | SC8480XP
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
pixel_values: uint16[1024, 1536]position_ids_cos: uint16[1024, 32]position_ids_sin: uint16[1024, 32]full_attention_mask: uint16[1, 1024, 1024]window_attention_mask: float16[1, 1024, 1024]Completion Time
10/17/2026, 9:30:12 AM
Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Windows: Windows 11 (28000)
- Build ID: APSS.WP_GL.1.0.r0-05000-SC8480XRELSFNWZA-4
- AI Hub: aihub-2026.10.10.0
Estimated Inference Time
62.3 ms
Estimated Peak Memory Usage
7 MB
Compute Units
NPU
1477
| Stage | Time | Memory |
|---|---|---|
First App Load | 799 ms | 17 MB |
Subsequent App Load | 731 ms | 17 MB |
Inference | 62.3 ms | 7 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
| default_graph_options.htp_options.enable_precision_compensation | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device