Geekbench ML Score

1300
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 09 2023 03:15 AM
Views 1

System Information

System Information
Operating System iOS 14.4.1
Model iPhone SE (2nd generation)
Model IDiPhone12,8
Motherboard D79AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 2.90 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1614
172.9 IPS
 
Image Classification (F16)
100% 1673
179.3 IPS
 
Image Classification (I8)
81% 368
39.4 IPS
 
Image Segmentation (F32)
100% 3420
21.1 IPS
 
Image Segmentation (F16)
100% 5413
33.4 IPS
 
Image Segmentation (I8)
89% 686
4.24 IPS
 
Pose Estimation (F32)
100% 1426
5.77 IPS
 
Pose Estimation (F16)
100% 4414
17.9 IPS
 
Pose Estimation (I8)
80% 127
0.51 IPS
 
Object Detection (F32)
100% 1447
50.8 IPS
 
Object Detection (F16)
99% 1694
59.5 IPS
 
Object Detection (I8)
52% 524
18.4 IPS
 
Face Detection (F32)
100% 3549
40.8 IPS
 
Face Detection (F16)
97% 4906
56.4 IPS
 
Face Detection (I8)
75% 522
5.99 IPS
 
Text Classification (F32)
100% 1006
397.8 IPS
 
Text Classification (F16)
98% 1232
487.3 IPS
 
Machine Translation (F32)
100% 1009
155.5 IPS
 
Machine Translation (F16)
100% 1005
154.8 IPS
 

Compare

Set Baseline Geekbench 6 now available