Geekbench ML Score

706
Core ML GPU Inference Score
Geekbench ML 0.6.0 for macOS AVX2

Result Information

Upload Date August 16 2024 09:35 PM
Views 2

System Information

System Information
Operating System macOS 14.6.1 (Build 23G93)
Model MacBook Pro (13-inch Mid 2018)
Model IDMacBookPro15,2
Motherboard Apple Inc. Mac-827FB448E656EC26 MacBookPro15,2
CPU Information
Name Intel Core i5-8259U
Topology 1 Processor, 4 Cores, 8 Threads
Identifier GenuineIntel Family 6 Model 142 Stepping 10
Base Frequency 2.30 GHz
Cluster 14 Cores
L1 Instruction Cache32.0 KB x 4
L1 Data Cache32.0 KB x 4
L2 Cache256 KB x 4
L3 Cache6.00 MB x 1
Memory Information
Size 8.00 GB
Transfer Rate2133 MT/s
Type LPDDR3
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 639
119.5 IPS
 
Image Classification (F16)
100% 424
79.4 IPS
 
Image Classification (I8)
99% 444
83.1 IPS
 
Image Segmentation (F32)
100% 182
3.03 IPS
 
Image Segmentation (F16)
100% 182
3.05 IPS
 
Image Segmentation (I8)
100% 190
3.17 IPS
 
Pose Estimation (F32)
100% 5806
7.03 IPS
 
Pose Estimation (F16)
100% 9532
11.5 IPS
 
Pose Estimation (I8)
100% 9909
12.0 IPS
 
Object Detection (F32)
100% 512
38.2 IPS
 
Object Detection (F16)
100% 494
36.9 IPS
 
Object Detection (I8)
97% 547
40.9 IPS
 
Face Detection (F32)
100% 1759
20.9 IPS
 
Face Detection (F16)
99% 1473
17.5 IPS
 
Face Detection (I8)
99% 1651
19.6 IPS
 
Depth Estimation (F32)
100% 978
7.58 IPS
 
Depth Estimation (F16)
100% 942
7.30 IPS
 
Depth Estimation (I8)
37% 915
7.09 IPS
 
Style Transfer (F32)
100% 1929
2.54 IPS
 
Style Transfer (F16)
100% 1896
2.49 IPS
 
Style Transfer (I8)
100% 1894
2.49 IPS
 
Image Super-Resolution (F32)
100% 474
16.9 IPS
 
Image Super-Resolution (F16)
100% 474
16.9 IPS
 
Image Super-Resolution (I8)
100% 470
16.8 IPS
 
Text Classification (F32)
100% 130
187.1 IPS
 
Text Classification (F16)
100% 137
197.1 IPS
 
Text Classification (I8)
92% 166
238.9 IPS
 
Machine Translation (F32)
100% 442
8.13 IPS
 
Machine Translation (F16)
100% 350
6.43 IPS
 
Machine Translation (I8)
99% 434
7.99 IPS
 

Compare

Set Baseline Geekbench 6 now available