Geekbench ML Score

1890
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2023 07:24 PM
Views 1

System Information

System Information
Operating System iOS 17.1.2
Model iPhone 13 mini
Model IDiPhone14,4
Motherboard D16AP
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 3.57 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1478
158.4 IPS
 
Image Classification (F16)
100% 2536
271.7 IPS
 
Image Classification (I8)
81% 633
67.8 IPS
 
Image Segmentation (F32)
100% 5028
31.1 IPS
 
Image Segmentation (F16)
100% 7200
44.5 IPS
 
Image Segmentation (I8)
89% 1124
6.94 IPS
 
Pose Estimation (F32)
100% 1979
8.01 IPS
 
Pose Estimation (F16)
100% 4321
17.5 IPS
 
Pose Estimation (I8)
80% 216
0.88 IPS
 
Object Detection (F32)
100% 1698
59.6 IPS
 
Object Detection (F16)
100% 3020
106.0 IPS
 
Object Detection (I8)
52% 913
32.0 IPS
 
Face Detection (F32)
100% 4850
55.7 IPS
 
Face Detection (F16)
97% 6286
72.2 IPS
 
Face Detection (I8)
75% 832
9.55 IPS
 
Text Classification (F32)
100% 1762
697.0 IPS
 
Text Classification (F16)
100% 1146
453.4 IPS
 
Machine Translation (F32)
100% 2059
317.3 IPS
 
Machine Translation (F16)
100% 2049
315.8 IPS
 

Compare

Set Baseline Geekbench 6 now available