Geekbench ML Score

4494
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 16 2024 02:25 AM
Views 3

System Information

System Information
Operating System iOS 17.5
Model iPad14,8
Model IDiPad14,8
Motherboard J507AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.47 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% 2820
527.8 IPS
 
Image Classification (F16)
100% 2880
539.0 IPS
 
Image Classification (I8)
99% 2656
497.1 IPS
 
Image Segmentation (F32)
100% 1387
23.2 IPS
 
Image Segmentation (F16)
100% 1438
24.0 IPS
 
Image Segmentation (I8)
100% 1441
24.1 IPS
 
Pose Estimation (F32)
100% 20724
25.1 IPS
 
Pose Estimation (F16)
100% 22635
27.4 IPS
 
Pose Estimation (I8)
100% 22145
26.8 IPS
 
Object Detection (F32)
100% 2107
157.3 IPS
 
Object Detection (F16)
100% 2647
197.6 IPS
 
Object Detection (I8)
97% 1243
92.8 IPS
 
Face Detection (F32)
100% 8883
105.6 IPS
 
Face Detection (F16)
98% 9931
118.1 IPS
 
Face Detection (I8)
97% 9525
113.3 IPS
 
Depth Estimation (F32)
100% 14841
115.1 IPS
 
Depth Estimation (F16)
100% 16239
125.9 IPS
 
Depth Estimation (I8)
37% 14908
115.6 IPS
 
Style Transfer (F32)
100% 36563
48.1 IPS
 
Style Transfer (F16)
100% 43132
56.7 IPS
 
Style Transfer (I8)
100% 42444
55.8 IPS
 
Image Super-Resolution (F32)
100% 6518
232.8 IPS
 
Image Super-Resolution (F16)
100% 5604
200.1 IPS
 
Image Super-Resolution (I8)
100% 6726
240.2 IPS
 
Text Classification (F32)
100% 1111
1.60 KIPS
 
Text Classification (F16)
100% 740
1.06 KIPS
 
Text Classification (I8)
96% 740
1.06 KIPS
 
Machine Translation (F32)
100% 647
11.9 IPS
 
Machine Translation (F16)
100% 680
12.5 IPS
 
Machine Translation (I8)
99% 641
11.8 IPS
 

Compare

Set Baseline Geekbench 6 now available