Geekbench ML Score

6560
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 21 2024 09:59 PM
Views 1

System Information

System Information
Operating System iOS 17.5
Model iPad16,6
Model IDiPad16,6
Motherboard J721AP
CPU Information
Name ARM
Topology 1 Processor, 10 Cores
Identifier ARM
Base Frequency 4.41 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% 4155
777.5 IPS
 
Image Classification (F16)
100% 4387
820.9 IPS
 
Image Classification (I8)
99% 4037
755.4 IPS
 
Image Segmentation (F32)
100% 2038
34.0 IPS
 
Image Segmentation (F16)
100% 2246
37.5 IPS
 
Image Segmentation (I8)
100% 2213
37.0 IPS
 
Pose Estimation (F32)
100% 26821
32.5 IPS
 
Pose Estimation (F16)
100% 28890
35.0 IPS
 
Pose Estimation (I8)
100% 28077
34.0 IPS
 
Object Detection (F32)
100% 3314
247.4 IPS
 
Object Detection (F16)
100% 3895
290.8 IPS
 
Object Detection (I8)
97% 3420
255.3 IPS
 
Face Detection (F32)
100% 11320
134.6 IPS
 
Face Detection (F16)
98% 13949
165.9 IPS
 
Face Detection (I8)
97% 13594
161.6 IPS
 
Depth Estimation (F32)
100% 19541
151.5 IPS
 
Depth Estimation (F16)
100% 21883
169.7 IPS
 
Depth Estimation (I8)
37% 20273
157.2 IPS
 
Style Transfer (F32)
100% 55594
73.1 IPS
 
Style Transfer (F16)
100% 64973
85.5 IPS
 
Style Transfer (I8)
100% 64493
84.8 IPS
 
Image Super-Resolution (F32)
100% 8099
289.2 IPS
 
Image Super-Resolution (F16)
100% 8736
312.0 IPS
 
Image Super-Resolution (I8)
100% 7881
281.4 IPS
 
Text Classification (F32)
100% 1236
1.78 KIPS
 
Text Classification (F16)
100% 1443
2.07 KIPS
 
Text Classification (I8)
96% 1136
1.63 KIPS
 
Machine Translation (F32)
100% 987
18.2 IPS
 
Machine Translation (F16)
100% 1038
19.1 IPS
 
Machine Translation (I8)
99% 896
16.5 IPS
 

Compare

Set Baseline Geekbench 6 now available