Geekbench ML Score

3501
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 18 2024 08:57 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 GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1878
351.5 IPS
 
Image Classification (F16)
100% 1541
288.3 IPS
 
Image Classification (I8)
99% 1443
270.0 IPS
 
Image Segmentation (F32)
100% 855
14.3 IPS
 
Image Segmentation (F16)
100% 851
14.2 IPS
 
Image Segmentation (I8)
100% 846
14.1 IPS
 
Pose Estimation (F32)
100% 16013
19.4 IPS
 
Pose Estimation (F16)
100% 17937
21.7 IPS
 
Pose Estimation (I8)
100% 17686
21.4 IPS
 
Object Detection (F32)
100% 1690
126.2 IPS
 
Object Detection (F16)
100% 1552
115.9 IPS
 
Object Detection (I8)
97% 1625
121.3 IPS
 
Face Detection (F32)
100% 6122
72.8 IPS
 
Face Detection (F16)
98% 7117
84.6 IPS
 
Face Detection (I8)
97% 7183
85.4 IPS
 
Depth Estimation (F32)
100% 12133
94.1 IPS
 
Depth Estimation (F16)
100% 13813
107.1 IPS
 
Depth Estimation (I8)
37% 12582
97.6 IPS
 
Style Transfer (F32)
100% 27602
36.3 IPS
 
Style Transfer (F16)
100% 31172
41.0 IPS
 
Style Transfer (I8)
100% 32024
42.1 IPS
 
Image Super-Resolution (F32)
100% 4797
171.3 IPS
 
Image Super-Resolution (F16)
100% 5522
197.2 IPS
 
Image Super-Resolution (I8)
100% 5868
209.6 IPS
 
Text Classification (F32)
100% 1169
1.68 KIPS
 
Text Classification (F16)
100% 764
1.10 KIPS
 
Text Classification (I8)
96% 759
1.09 KIPS
 
Machine Translation (F32)
100% 579
10.7 IPS
 
Machine Translation (F16)
100% 592
10.9 IPS
 
Machine Translation (I8)
99% 583
10.7 IPS
 

Compare

Set Baseline Geekbench 6 now available