realme RMX3491
Geekbench ML Score
253
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 13 2023 06:12 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | realme RMX3491 |
| Model ID | realme RMX3491 |
| Motherboard | bengal |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3337 revision 0 |
| Base Frequency | 1.90 GHz |
| Cluster 1 | 4 Cores @ 1.90 GHz |
| Cluster 2 | 4 Cores @ 2.40 GHz |
| Memory Information | |
|---|---|
| Size | 3.53 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
149
16.0 IPS |
|
|
Image Classification (F16)
|
100% |
297
31.8 IPS |
|
|
Image Classification (I8)
|
80% |
261
27.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
317
1.96 IPS |
|
|
Image Segmentation (F16)
|
100% |
624
3.85 IPS |
|
|
Image Segmentation (I8)
|
89% |
571
3.53 IPS |
|
|
Pose Estimation (F32)
|
100% |
141
0.57 IPS |
|
|
Pose Estimation (F16)
|
100% |
265
1.07 IPS |
|
|
Pose Estimation (I8)
|
80% |
265
1.07 IPS |
|
|
Object Detection (F32)
|
100% |
133
4.68 IPS |
|
|
Object Detection (F16)
|
99% |
191
6.69 IPS |
|
|
Object Detection (I8)
|
53% |
181
6.35 IPS |
|
|
Face Detection (F32)
|
100% |
312
3.58 IPS |
|
|
Face Detection (F16)
|
97% |
546
6.27 IPS |
|
|
Face Detection (I8)
|
76% |
487
5.60 IPS |
|
|
Text Classification (F32)
|
100% |
180
71.2 IPS |
|
|
Text Classification (F16)
|
98% |
231
91.5 IPS |
|
|
Machine Translation (F32)
|
100% |
150
23.2 IPS |
|
|
Machine Translation (F16)
|
100% |
152
23.4 IPS |
