Geekbench ML Score

295
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date February 23 2024 02:30 AM
Views 1

System Information

System Information
Operating System iOS 17.3.1
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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1070
200.2 IPS
 
Image Classification (F16)
100% 970
181.4 IPS
 
Image Classification (I8)
99% 969
181.3 IPS
 
Image Segmentation (F32)
100% 449
7.49 IPS
 
Image Segmentation (F16)
100% 412
6.87 IPS
 
Image Segmentation (I8)
100% 411
6.87 IPS
 
Pose Estimation (F32)
100% 5515
6.68 IPS
 
Pose Estimation (F16)
100% 11119
13.5 IPS
 
Pose Estimation (I8)
100% 11085
13.4 IPS
 
Object Detection (F32)
100% 1089
81.3 IPS
 
Object Detection (F16)
100% 1069
79.8 IPS
 
Object Detection (I8)
97% 1102
82.3 IPS
 
Face Detection (F32)
100% 2180
25.9 IPS
 
Face Detection (F16)
100% 1812
21.5 IPS
 
Face Detection (I8)
99% 1798
21.4 IPS
 
Depth Estimation (F32)
100% 3813
29.6 IPS
 
Depth Estimation (F16)
99% 4089
31.7 IPS
 
Depth Estimation (I8)
99% 4086
31.7 IPS
 
Style Transfer (F32)
100% 10504
13.8 IPS
 
Style Transfer (F16)
100% 12511
16.5 IPS
 
Style Transfer (I8)
100% 12557
16.5 IPS
 
Image Super-Resolution (F32)
0
 
Image Super-Resolution (F16)
0
 
Image Super-Resolution (I8)
100% 2753
98.3 IPS
 
Text Classification (F32)
0
 
Text Classification (F16)
0
 
Text Classification (I8)
0
 
Machine Translation (F32)
0
 
Machine Translation (F16)
0
 
Machine Translation (I8)
0
 

Compare

Set Baseline Geekbench 6 now available