Profile Job Results
Jobs
jglwmenlp
Results Ready
Name
minilm_v2
Target Device
- Dragonwing Q-6690 MTP
- Android 15
- Qualcomm® Dragonwing™ Q-6690 | QCM6690
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[1, 128]attention_mask: int32[1, 128]Completion Time
10/3/2026, 7:53:57 PM
Versions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Android: 15 (AQ3A.250330.001)
- Build ID: QCM6690.LA.1.0.r1-00117-STD.PROD-1
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
12.1 ms
Estimated Peak Memory Usage
0 ‑ 50 MB
Compute Units
NPU
181
CPU
125
GPU
10
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.76 s | 102‑109 MB |
Subsequent App Load | 436 ms | 38‑77 MB |
Inference | 12.1 ms | 0‑50 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device