Geekbench ML Score

1826
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date March 10 2022 11:42 AM
Views 5

System Information

System Information
Operating System iOS 15.3.1
Model iPhone 13 mini
Model IDiPhone14,4
Motherboard D16AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.61 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1173
125.6 IPS
 
Image Classification (F16)
100% 2532
271.2 IPS
 
Image Classification (I8)
81% 640
68.6 IPS
 
Image Segmentation (F32)
100% 5318
32.8 IPS
 
Image Segmentation (F16)
100% 7244
44.7 IPS
 
Image Segmentation (I8)
89% 1094
6.75 IPS
 
Pose Estimation (F32)
100% 1686
6.82 IPS
 
Pose Estimation (F16)
100% 4208
17.0 IPS
 
Pose Estimation (I8)
80% 207
0.84 IPS
 
Object Detection (F32)
100% 1640
57.6 IPS
 
Object Detection (F16)
100% 3021
106.0 IPS
 
Object Detection (I8)
52% 869
30.5 IPS
 
Face Detection (F32)
100% 4823
55.4 IPS
 
Face Detection (F16)
97% 6105
70.1 IPS
 
Face Detection (I8)
75% 823
9.45 IPS
 
Text Classification (F32)
100% 982
388.5 IPS
 
Text Classification (F16)
100% 1999
790.8 IPS
 
Machine Translation (F32)
100% 1981
305.4 IPS
 
Machine Translation (F16)
100% 1968
303.3 IPS
 

Compare

Set Baseline Geekbench 6 now available