Geekbench ML Score

620
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date October 28 2024 08:04 PM
Views 1

System Information

System Information
Operating System iOS 16.7.10
Model iPhone 8
Model IDiPhone10,1
Motherboard D20AP
CPU Information
Name Apple A11 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.39 GHz
Cluster 12 Cores
Cluster 24 Cores
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 1.93 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 176
33.0 IPS
 
Image Classification (F16)
100% 142
26.5 IPS
 
Image Classification (I8)
99% 144
26.9 IPS
 
Image Segmentation (F32)
100% 185
3.10 IPS
 
Image Segmentation (F16)
100% 198
3.30 IPS
 
Image Segmentation (I8)
100% 198
3.31 IPS
 
Pose Estimation (F32)
100% 2246
2.72 IPS
 
Pose Estimation (F16)
100% 2569
3.11 IPS
 
Pose Estimation (I8)
100% 2651
3.21 IPS
 
Object Detection (F32)
100% 297
22.1 IPS
 
Object Detection (F16)
100% 266
19.9 IPS
 
Object Detection (I8)
97% 302
22.6 IPS
 
Face Detection (F32)
100% 935
11.1 IPS
 
Face Detection (F16)
100% 990
11.8 IPS
 
Face Detection (I8)
99% 969
11.5 IPS
 
Depth Estimation (F32)
100% 2303
17.9 IPS
 
Depth Estimation (F16)
100% 2344
18.2 IPS
 
Depth Estimation (I8)
99% 2541
19.7 IPS
 
Style Transfer (F32)
100% 4825
6.35 IPS
 
Style Transfer (F16)
100% 5155
6.78 IPS
 
Style Transfer (I8)
100% 4710
6.20 IPS
 
Image Super-Resolution (F32)
100% 962
34.3 IPS
 
Image Super-Resolution (F16)
100% 1128
40.3 IPS
 
Image Super-Resolution (I8)
100% 1024
36.6 IPS
 
Text Classification (F32)
100% 48
69.2 IPS
 
Text Classification (F16)
100% 201
289.4 IPS
 
Text Classification (I8)
96% 201
289.4 IPS
 
Machine Translation (F32)
100% 317
5.83 IPS
 
Machine Translation (F16)
100% 224
4.12 IPS
 
Machine Translation (I8)
99% 282
5.18 IPS
 

Compare

Set Baseline Geekbench 6 now available