Geekbench ML Score

6337
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date June 11 2024 07:10 PM
Views 1

System Information

System Information
Operating System iOS 17.5.1
Model iPad16,6
Model IDiPad16,6
Motherboard J721AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.44 GHz
Cluster 14 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.05 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4409
825.0 IPS
 
Image Classification (F16)
100% 4517
845.3 IPS
 
Image Classification (I8)
99% 4082
763.8 IPS
 
Image Segmentation (F32)
100% 1905
31.8 IPS
 
Image Segmentation (F16)
100% 2277
38.0 IPS
 
Image Segmentation (I8)
100% 2223
37.1 IPS
 
Pose Estimation (F32)
100% 26871
32.5 IPS
 
Pose Estimation (F16)
100% 28904
35.0 IPS
 
Pose Estimation (I8)
100% 28023
33.9 IPS
 
Object Detection (F32)
100% 2077
155.0 IPS
 
Object Detection (F16)
100% 2706
202.0 IPS
 
Object Detection (I8)
97% 2490
185.9 IPS
 
Face Detection (F32)
100% 11190
133.0 IPS
 
Face Detection (F16)
98% 9966
118.5 IPS
 
Face Detection (I8)
97% 13012
154.7 IPS
 
Depth Estimation (F32)
100% 20585
159.6 IPS
 
Depth Estimation (F16)
100% 23102
179.2 IPS
 
Depth Estimation (I8)
37% 20901
162.1 IPS
 
Style Transfer (F32)
100% 55281
72.7 IPS
 
Style Transfer (F16)
100% 65149
85.7 IPS
 
Style Transfer (I8)
100% 65485
86.1 IPS
 
Image Super-Resolution (F32)
100% 10956
391.3 IPS
 
Image Super-Resolution (F16)
100% 10004
357.3 IPS
 
Image Super-Resolution (I8)
100% 11535
411.9 IPS
 
Text Classification (F32)
100% 1167
1.68 KIPS
 
Text Classification (F16)
100% 1082
1.56 KIPS
 
Text Classification (I8)
96% 825
1.19 KIPS
 
Machine Translation (F32)
100% 1071
19.7 IPS
 
Machine Translation (F16)
100% 1032
19.0 IPS
 
Machine Translation (I8)
99% 966
17.8 IPS
 

Compare

Set Baseline Geekbench 6 now available