Geekbench ML Score

798
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date January 21 2024 01:02 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% 994
186.0 IPS
 
Image Classification (F16)
100% 450
84.2 IPS
 
Image Classification (I8)
99% 539
100.8 IPS
 
Image Segmentation (F32)
100% 287
4.80 IPS
 
Image Segmentation (F16)
100% 263
4.39 IPS
 
Image Segmentation (I8)
100% 176
2.94 IPS
 
Pose Estimation (F32)
100% 2932
3.55 IPS
 
Pose Estimation (F16)
100% 5887
7.13 IPS
 
Pose Estimation (I8)
100% 3190
3.86 IPS
 
Object Detection (F32)
100% 500
37.3 IPS
 
Object Detection (F16)
100% 591
44.1 IPS
 
Object Detection (I8)
97% 391
29.2 IPS
 
Face Detection (F32)
100% 853
10.1 IPS
 
Face Detection (F16)
100% 801
9.52 IPS
 
Face Detection (I8)
99% 618
7.35 IPS
 
Depth Estimation (F32)
100% 1547
12.0 IPS
 
Depth Estimation (F16)
99% 1692
13.1 IPS
 
Depth Estimation (I8)
99% 2329
18.1 IPS
 
Style Transfer (F32)
100% 4574
6.02 IPS
 
Style Transfer (F16)
100% 6889
9.06 IPS
 
Style Transfer (I8)
100% 5059
6.66 IPS
 
Image Super-Resolution (F32)
100% 221
7.89 IPS
 
Image Super-Resolution (F16)
100% 1374
49.1 IPS
 
Image Super-Resolution (I8)
100% 1385
49.4 IPS
 
Text Classification (F32)
100% 194
278.2 IPS
 
Text Classification (F16)
100% 222
318.9 IPS
 
Text Classification (I8)
96% 94
135.7 IPS
 
Machine Translation (F32)
100% 504
9.28 IPS
 
Machine Translation (F16)
99% 414
7.61 IPS
 
Machine Translation (I8)
99% 400
7.37 IPS
 

Compare

Set Baseline Geekbench 6 now available