Geekbench ML Score

1380
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 17 2021 12:46 PM
Views 1

System Information

System Information
Operating System iOS 15.0
Model iPhone 11 Pro Max
Model IDiPhone12,5
Motherboard D431AP
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 3.66 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1238
132.7 IPS
 
Image Classification (F16)
100% 1580
169.3 IPS
 
Image Classification (I8)
81% 449
48.1 IPS
 
Image Segmentation (F32)
100% 3429
21.2 IPS
 
Image Segmentation (F16)
100% 5393
33.3 IPS
 
Image Segmentation (I8)
89% 837
5.17 IPS
 
Pose Estimation (F32)
100% 1418
5.74 IPS
 
Pose Estimation (F16)
100% 4409
17.8 IPS
 
Pose Estimation (I8)
80% 152
0.62 IPS
 
Object Detection (F32)
100% 1563
54.9 IPS
 
Object Detection (F16)
99% 1863
65.4 IPS
 
Object Detection (I8)
52% 639
22.4 IPS
 
Face Detection (F32)
100% 3621
41.6 IPS
 
Face Detection (F16)
97% 5098
58.6 IPS
 
Face Detection (I8)
75% 624
7.16 IPS
 
Text Classification (F32)
100% 961
380.0 IPS
 
Text Classification (F16)
98% 1203
475.8 IPS
 
Machine Translation (F32)
100% 1185
182.6 IPS
 
Machine Translation (F16)
100% 1209
186.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download