Profile Job Results
Jobs
jgd3oj0rp
Results Ready
Name
grootn15_llm
Target Device
- Arduino VENTUNO Q
- Ubuntu 24.04
- Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_embeds: float32[1, 384, 2048]llm_attention_mask: float32[1, 1, 384, 384]Completion Time
8/22/2026, 9:37:54 AM
Versions
- ONNX Runtime: 1.27.1
- QAIRT: v2.45.0.260326154327
- Qualcomm Linux: 24.04
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
132 ms
Estimated Peak Memory Usage
6 ‑ 13 MB
Compute Units
NPU
712
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.31 s | 1 GB |
Subsequent App Load | 1.43 s | 1 GB |
Inference | 132 ms | 6‑13 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device