Geekbench ML Score

2324
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 30 2022 03:27 AM
Views 2

System Information

System Information
Operating System iOS 16.0
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% 2822
302.4 IPS
 
Image Classification (F16)
100% 4372
468.5 IPS
 
Image Classification (I8)
81% 696
74.6 IPS
 
Image Segmentation (F32)
100% 5897
36.4 IPS
 
Image Segmentation (F16)
100% 8233
50.9 IPS
 
Image Segmentation (I8)
89% 1249
7.72 IPS
 
Pose Estimation (F32)
100% 1916
7.75 IPS
 
Pose Estimation (F16)
100% 4877
19.7 IPS
 
Pose Estimation (I8)
80% 238
0.96 IPS
 
Object Detection (F32)
100% 3244
113.9 IPS
 
Object Detection (F16)
100% 3383
118.7 IPS
 
Object Detection (I8)
52% 993
34.9 IPS
 
Face Detection (F32)
100% 5115
58.8 IPS
 
Face Detection (F16)
97% 9254
106.3 IPS
 
Face Detection (I8)
75% 918
10.5 IPS
 
Text Classification (F32)
100% 1909
755.1 IPS
 
Text Classification (F16)
100% 2124
839.9 IPS
 
Machine Translation (F32)
100% 2022
311.7 IPS
 
Machine Translation (F16)
100% 2029
312.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download