Geekbench ML Score

3469
Core ML CPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date May 08 2024 02:50 PM
Views 2

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model MacBook Pro (14-inch, 2023)
Model IDMac14,5
Motherboard Mac14,5
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.46 GHz
Cluster 18 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 32.00 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1428
267.2 IPS
 
Image Classification (F16)
100% 1772
331.5 IPS
 
Image Classification (I8)
99% 1776
332.4 IPS
 
Image Segmentation (F32)
100% 881
14.7 IPS
 
Image Segmentation (F16)
100% 870
14.5 IPS
 
Image Segmentation (I8)
100% 860
14.4 IPS
 
Pose Estimation (F32)
100% 6037
7.31 IPS
 
Pose Estimation (F16)
100% 14091
17.1 IPS
 
Pose Estimation (I8)
100% 14325
17.3 IPS
 
Object Detection (F32)
100% 1439
107.5 IPS
 
Object Detection (F16)
100% 1990
148.5 IPS
 
Object Detection (I8)
97% 1471
109.8 IPS
 
Face Detection (F32)
100% 2890
34.4 IPS
 
Face Detection (F16)
97% 4229
50.3 IPS
 
Face Detection (I8)
97% 4318
51.3 IPS
 
Depth Estimation (F32)
100% 5539
43.0 IPS
 
Depth Estimation (F16)
100% 8507
66.0 IPS
 
Depth Estimation (I8)
99% 8516
66.0 IPS
 
Style Transfer (F32)
100% 16067
21.1 IPS
 
Style Transfer (F16)
100% 26608
35.0 IPS
 
Style Transfer (I8)
100% 26632
35.0 IPS
 
Image Super-Resolution (F32)
100% 3905
139.5 IPS
 
Image Super-Resolution (F16)
100% 5216
186.3 IPS
 
Image Super-Resolution (I8)
100% 5150
183.9 IPS
 
Text Classification (F32)
100% 2149
3.09 KIPS
 
Text Classification (F16)
100% 3072
4.42 KIPS
 
Text Classification (I8)
96% 3024
4.35 KIPS
 
Machine Translation (F32)
100% 1144
21.1 IPS
 
Machine Translation (F16)
100% 1493
27.5 IPS
 
Machine Translation (I8)
99% 1234
22.7 IPS
 

Compare

Set Baseline Geekbench 6 now available