Geekbench ML Score

1071
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date January 21 2024 01:14 PM
Views 1

System Information

System Information
Operating System iOS 17.2
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% 450
84.2 IPS
 
Image Classification (F16)
100% 541
101.3 IPS
 
Image Classification (I8)
99% 892
166.9 IPS
 
Image Segmentation (F32)
100% 317
5.29 IPS
 
Image Segmentation (F16)
100% 290
4.84 IPS
 
Image Segmentation (I8)
100% 300
5.02 IPS
 
Pose Estimation (F32)
100% 2834
3.43 IPS
 
Pose Estimation (F16)
100% 10528
12.7 IPS
 
Pose Estimation (I8)
100% 8702
10.5 IPS
 
Object Detection (F32)
100% 891
66.5 IPS
 
Object Detection (F16)
100% 456
34.0 IPS
 
Object Detection (I8)
97% 633
47.2 IPS
 
Face Detection (F32)
100% 1219
14.5 IPS
 
Face Detection (F16)
100% 1361
16.2 IPS
 
Face Detection (I8)
99% 859
10.2 IPS
 
Depth Estimation (F32)
100% 2269
17.6 IPS
 
Depth Estimation (F16)
99% 2382
18.5 IPS
 
Depth Estimation (I8)
99% 3638
28.2 IPS
 
Style Transfer (F32)
100% 6307
8.30 IPS
 
Style Transfer (F16)
100% 5916
7.78 IPS
 
Style Transfer (I8)
100% 7022
9.24 IPS
 
Image Super-Resolution (F32)
100% 1083
38.7 IPS
 
Image Super-Resolution (F16)
100% 976
34.8 IPS
 
Image Super-Resolution (I8)
100% 1191
42.5 IPS
 
Text Classification (F32)
100% 560
804.2 IPS
 
Text Classification (F16)
100% 266
383.0 IPS
 
Text Classification (I8)
96% 710
1.02 KIPS
 
Machine Translation (F32)
100% 380
6.99 IPS
 
Machine Translation (F16)
99% 360
6.63 IPS
 
Machine Translation (I8)
99% 149
2.75 IPS
 

Compare

Set Baseline Geekbench 6 now available