Geekbench ML Score

2264
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 30 2022 02:38 AM
Views 1

System Information

System Information
Operating System iOS 16.0.2
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2828
303.0 IPS
 
Image Classification (F16)
100% 4375
468.8 IPS
 
Image Classification (I8)
81% 697
74.7 IPS
 
Image Segmentation (F32)
100% 5861
36.2 IPS
 
Image Segmentation (F16)
100% 8129
50.2 IPS
 
Image Segmentation (I8)
89% 1275
7.87 IPS
 
Pose Estimation (F32)
100% 1911
7.73 IPS
 
Pose Estimation (F16)
100% 4879
19.7 IPS
 
Pose Estimation (I8)
80% 241
0.98 IPS
 
Object Detection (F32)
100% 3297
115.7 IPS
 
Object Detection (F16)
100% 3332
116.9 IPS
 
Object Detection (I8)
52% 994
34.9 IPS
 
Face Detection (F32)
100% 5105
58.7 IPS
 
Face Detection (F16)
97% 9229
106.0 IPS
 
Face Detection (I8)
75% 971
11.2 IPS
 
Text Classification (F32)
100% 1512
598.1 IPS
 
Text Classification (F16)
100% 1515
599.3 IPS
 
Machine Translation (F32)
100% 2028
312.5 IPS
 
Machine Translation (F16)
100% 2034
313.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download