Geekbench ML Score

2021
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date July 04 2024 06:14 AM
Views 2

System Information

System Information
Operating System iOS 16.5
Model iPad Pro (12.9-inch, 6th generation)
Model IDiPad14,5
Motherboard J620AP
CPU Information
Name Apple M2
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.49 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 7.33 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1014
189.7 IPS
 
Image Classification (F16)
100% 968
181.2 IPS
 
Image Classification (I8)
99% 969
181.2 IPS
 
Image Segmentation (F32)
100% 696
11.6 IPS
 
Image Segmentation (F16)
100% 610
10.2 IPS
 
Image Segmentation (I8)
100% 610
10.2 IPS
 
Pose Estimation (F32)
100% 5802
7.03 IPS
 
Pose Estimation (F16)
100% 10077
12.2 IPS
 
Pose Estimation (I8)
100% 10074
12.2 IPS
 
Object Detection (F32)
100% 1070
79.9 IPS
 
Object Detection (F16)
100% 1090
81.4 IPS
 
Object Detection (I8)
97% 1085
81.0 IPS
 
Face Detection (F32)
100% 2016
24.0 IPS
 
Face Detection (F16)
100% 1764
21.0 IPS
 
Face Detection (I8)
99% 1763
21.0 IPS
 
Depth Estimation (F32)
100% 3560
27.6 IPS
 
Depth Estimation (F16)
99% 3887
30.1 IPS
 
Depth Estimation (I8)
99% 3878
30.1 IPS
 
Style Transfer (F32)
100% 10795
14.2 IPS
 
Style Transfer (F16)
100% 12462
16.4 IPS
 
Style Transfer (I8)
100% 12441
16.4 IPS
 
Image Super-Resolution (F32)
100% 2474
88.4 IPS
 
Image Super-Resolution (F16)
100% 2628
93.9 IPS
 
Image Super-Resolution (I8)
100% 2613
93.3 IPS
 
Text Classification (F32)
100% 930
1.34 KIPS
 
Text Classification (F16)
100% 451
648.5 IPS
 
Text Classification (I8)
96% 589
846.4 IPS
 
Machine Translation (F32)
100% 1395
25.7 IPS
 
Machine Translation (F16)
99% 1795
33.0 IPS
 
Machine Translation (I8)
99% 1368
25.2 IPS
 

Compare

Set Baseline Geekbench 6 now available