Geekbench ML Score

1393
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 06:41 PM
Views 2

System Information

System Information
Operating System iOS 16.1.2
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% 1890
202.6 IPS
 
Image Classification (F16)
100% 2708
290.1 IPS
 
Image Classification (I8)
81% 297
31.8 IPS
 
Image Segmentation (F32)
100% 5724
35.4 IPS
 
Image Segmentation (F16)
100% 8009
49.5 IPS
 
Image Segmentation (I8)
89% 544
3.36 IPS
 
Pose Estimation (F32)
100% 1709
6.92 IPS
 
Pose Estimation (F16)
100% 4866
19.7 IPS
 
Pose Estimation (I8)
80% 103
0.42 IPS
 
Object Detection (F32)
100% 1890
66.3 IPS
 
Object Detection (F16)
100% 2609
91.5 IPS
 
Object Detection (I8)
52% 422
14.8 IPS
 
Face Detection (F32)
100% 3659
42.0 IPS
 
Face Detection (F16)
97% 6174
70.9 IPS
 
Face Detection (I8)
75% 417
4.79 IPS
 
Text Classification (F32)
100% 929
367.5 IPS
 
Text Classification (F16)
100% 1043
412.5 IPS
 
Machine Translation (F32)
100% 939
144.7 IPS
 
Machine Translation (F16)
100% 950
146.5 IPS
 

Compare

Set Baseline