Geekbench ML Score

1958
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 06:18 PM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad mini (6th generation)
Model IDiPad14,1
Motherboard J310AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.92 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 3.78 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 608
113.7 IPS
 
Image Classification (F16)
100% 606
113.3 IPS
 
Image Classification (I8)
99% 566
105.9 IPS
 
Image Segmentation (F32)
100% 1037
17.3 IPS
 
Image Segmentation (F16)
100% 1015
16.9 IPS
 
Image Segmentation (I8)
100% 1017
17.0 IPS
 
Pose Estimation (F32)
100% 10236
12.4 IPS
 
Pose Estimation (F16)
100% 11214
13.6 IPS
 
Pose Estimation (I8)
100% 11014
13.3 IPS
 
Object Detection (F32)
100% 796
59.4 IPS
 
Object Detection (F16)
100% 730
54.5 IPS
 
Object Detection (I8)
97% 697
52.1 IPS
 
Face Detection (F32)
100% 3243
38.6 IPS
 
Face Detection (F16)
98% 3315
39.4 IPS
 
Face Detection (I8)
97% 3825
45.5 IPS
 
Depth Estimation (F32)
100% 6769
52.5 IPS
 
Depth Estimation (F16)
100% 6163
47.8 IPS
 
Depth Estimation (I8)
37% 6974
54.1 IPS
 
Style Transfer (F32)
100% 18308
24.1 IPS
 
Style Transfer (F16)
100% 22504
29.6 IPS
 
Style Transfer (I8)
100% 22501
29.6 IPS
 
Image Super-Resolution (F32)
100% 2574
91.9 IPS
 
Image Super-Resolution (F16)
100% 2511
89.7 IPS
 
Image Super-Resolution (I8)
100% 2562
91.5 IPS
 
Text Classification (F32)
100% 359
515.8 IPS
 
Text Classification (F16)
100% 400
574.9 IPS
 
Text Classification (I8)
96% 227
326.1 IPS
 
Machine Translation (F32)
100% 449
8.26 IPS
 
Machine Translation (F16)
100% 459
8.46 IPS
 
Machine Translation (I8)
99% 408
7.52 IPS
 

Compare

Set Baseline Geekbench 6 now available