Geekbench ML Score

1309
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 01 2024 08:34 AM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPhone 12 Mini
Model IDiPhone13,1
Motherboard D52gAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
Cluster 12 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 3.57 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 414
77.5 IPS
 
Image Classification (F16)
100% 352
65.8 IPS
 
Image Classification (I8)
99% 344
64.4 IPS
 
Image Segmentation (F32)
100% 557
9.31 IPS
 
Image Segmentation (F16)
100% 585
9.77 IPS
 
Image Segmentation (I8)
100% 600
10.0 IPS
 
Pose Estimation (F32)
100% 5691
6.89 IPS
 
Pose Estimation (F16)
100% 6075
7.36 IPS
 
Pose Estimation (I8)
100% 5982
7.24 IPS
 
Object Detection (F32)
100% 529
39.5 IPS
 
Object Detection (F16)
100% 547
40.8 IPS
 
Object Detection (I8)
97% 484
36.1 IPS
 
Face Detection (F32)
100% 2769
32.9 IPS
 
Face Detection (F16)
98% 2314
27.5 IPS
 
Face Detection (I8)
97% 3113
37.0 IPS
 
Depth Estimation (F32)
100% 5372
41.7 IPS
 
Depth Estimation (F16)
100% 5597
43.4 IPS
 
Depth Estimation (I8)
37% 5425
42.1 IPS
 
Style Transfer (F32)
100% 11316
14.9 IPS
 
Style Transfer (F16)
100% 13720
18.0 IPS
 
Style Transfer (I8)
100% 13625
17.9 IPS
 
Image Super-Resolution (F32)
100% 1737
62.0 IPS
 
Image Super-Resolution (F16)
100% 1658
59.2 IPS
 
Image Super-Resolution (I8)
100% 1548
55.3 IPS
 
Text Classification (F32)
100% 248
356.9 IPS
 
Text Classification (F16)
100% 249
357.4 IPS
 
Text Classification (I8)
96% 164
235.3 IPS
 
Machine Translation (F32)
100% 323
5.94 IPS
 
Machine Translation (F16)
100% 343
6.31 IPS
 
Machine Translation (I8)
99% 332
6.10 IPS
 

Compare

Set Baseline Geekbench 6 now available