Geekbench ML Score

1610
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 19 2022 10:20 AM
Views 2

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 12 Pro Max
Model IDiPhone13,4
Motherboard D54pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.57 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1344
144.0 IPS
 
Image Classification (F16)
100% 1530
164.0 IPS
 
Image Classification (I8)
81% 642
68.8 IPS
 
Image Segmentation (F32)
100% 4215
26.0 IPS
 
Image Segmentation (F16)
100% 5861
36.2 IPS
 
Image Segmentation (I8)
89% 1170
7.23 IPS
 
Pose Estimation (F32)
100% 1471
5.95 IPS
 
Pose Estimation (F16)
100% 4992
20.2 IPS
 
Pose Estimation (I8)
80% 221
0.89 IPS
 
Object Detection (F32)
100% 1644
57.7 IPS
 
Object Detection (F16)
99% 1690
59.3 IPS
 
Object Detection (I8)
52% 916
32.1 IPS
 
Face Detection (F32)
100% 4286
49.2 IPS
 
Face Detection (F16)
97% 5474
62.9 IPS
 
Face Detection (I8)
75% 886
10.2 IPS
 
Text Classification (F32)
100% 851
336.8 IPS
 
Text Classification (F16)
98% 1095
433.2 IPS
 
Machine Translation (F32)
100% 1677
258.5 IPS
 
Machine Translation (F16)
100% 1675
258.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download