Geekbench ML Score

3460
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 22 2024 02:26 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad Air (5th generation)
Model IDiPad13,16
Motherboard J407AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.47 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1727
323.3 IPS
 
Image Classification (F16)
100% 1336
250.1 IPS
 
Image Classification (I8)
99% 1268
237.2 IPS
 
Image Segmentation (F32)
100% 835
14.0 IPS
 
Image Segmentation (F16)
100% 884
14.8 IPS
 
Image Segmentation (I8)
100% 832
13.9 IPS
 
Pose Estimation (F32)
100% 16145
19.6 IPS
 
Pose Estimation (F16)
100% 18071
21.9 IPS
 
Pose Estimation (I8)
100% 17663
21.4 IPS
 
Object Detection (F32)
100% 1475
110.1 IPS
 
Object Detection (F16)
100% 1504
112.3 IPS
 
Object Detection (I8)
97% 1555
116.1 IPS
 
Face Detection (F32)
100% 6043
71.9 IPS
 
Face Detection (F16)
98% 7268
86.4 IPS
 
Face Detection (I8)
97% 7318
87.0 IPS
 
Depth Estimation (F32)
100% 12400
96.2 IPS
 
Depth Estimation (F16)
100% 14049
109.0 IPS
 
Depth Estimation (I8)
37% 12775
99.1 IPS
 
Style Transfer (F32)
100% 28368
37.3 IPS
 
Style Transfer (F16)
100% 31290
41.2 IPS
 
Style Transfer (I8)
100% 34162
44.9 IPS
 
Image Super-Resolution (F32)
100% 4920
175.7 IPS
 
Image Super-Resolution (F16)
100% 5600
200.0 IPS
 
Image Super-Resolution (I8)
100% 5899
210.7 IPS
 
Text Classification (F32)
100% 1172
1.68 KIPS
 
Text Classification (F16)
100% 757
1.09 KIPS
 
Text Classification (I8)
96% 760
1.09 KIPS
 
Machine Translation (F32)
100% 573
10.5 IPS
 
Machine Translation (F16)
100% 587
10.8 IPS
 
Machine Translation (I8)
99% 585
10.8 IPS
 

Compare

Set Baseline Geekbench 6 now available