Geekbench ML Score

3001
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 09 2024 10:44 AM
Views 1

System Information

System Information
Operating System iOS 17.5
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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1301
243.5 IPS
 
Image Classification (F16)
100% 1680
314.3 IPS
 
Image Classification (I8)
99% 1681
314.6 IPS
 
Image Segmentation (F32)
100% 595
9.94 IPS
 
Image Segmentation (F16)
100% 594
9.93 IPS
 
Image Segmentation (I8)
100% 596
9.96 IPS
 
Pose Estimation (F32)
100% 5631
6.82 IPS
 
Pose Estimation (F16)
100% 12933
15.7 IPS
 
Pose Estimation (I8)
100% 12945
15.7 IPS
 
Object Detection (F32)
100% 1266
94.5 IPS
 
Object Detection (F16)
100% 1747
130.4 IPS
 
Object Detection (I8)
97% 1278
95.4 IPS
 
Face Detection (F32)
100% 2379
28.3 IPS
 
Face Detection (F16)
97% 4005
47.6 IPS
 
Face Detection (I8)
97% 4015
47.7 IPS
 
Depth Estimation (F32)
100% 5181
40.2 IPS
 
Depth Estimation (F16)
100% 8149
63.2 IPS
 
Depth Estimation (I8)
99% 8179
63.4 IPS
 
Style Transfer (F32)
100% 15618
20.5 IPS
 
Style Transfer (F16)
100% 24355
32.0 IPS
 
Style Transfer (I8)
100% 24371
32.1 IPS
 
Image Super-Resolution (F32)
100% 3502
125.1 IPS
 
Image Super-Resolution (F16)
100% 4530
161.8 IPS
 
Image Super-Resolution (I8)
100% 4548
162.4 IPS
 
Text Classification (F32)
100% 2111
3.03 KIPS
 
Text Classification (F16)
100% 3391
4.87 KIPS
 
Text Classification (I8)
96% 3381
4.86 KIPS
 
Machine Translation (F32)
100% 733
13.5 IPS
 
Machine Translation (F16)
100% 869
16.0 IPS
 
Machine Translation (I8)
99% 741
13.6 IPS
 

Compare

Set Baseline Geekbench 6 now available