Profile Job Results
Jobs
jp8jydwx5
Results Ready
Name
grootn15_vlm_proj
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
vlm_embeds: float32[1, 384, 2048]vlm_attention_mask: float32[1, 32, 384, 384]Completion Time
10/4/2026, 6:36:33 AM
Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
28.2 ms
Estimated Peak Memory Usage
21 ‑ 28 MB
Compute Units
NPU
195
| Stage | Time | Memory |
|---|---|---|
First App Load | 542 ms | 1‑8 MB |
Subsequent App Load | 297 ms | 1‑8 MB |
Inference | 28.2 ms | 21‑28 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device