Geekbench AI Score

2351
Single Precision Score
14933
Half Precision Score
16776
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

User stanleyruppert
Upload Date September 11 2024 02:55 AM
Views 7

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Max
System Information
Operating System macOS 14.6.1 (Build 23G93)
Model Mac Studio (2023)
Model IDMac14,13
Motherboard Mac14,13
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.48 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1118
207.9 IPS
 
Image Classification (HP)
100% 7767
1.44 KIPS
 
Image Classification (Q)
96% 8269
1.54 KIPS
 
Image Segmentation (SP)
100% 738
12.0 IPS
 
Image Segmentation (HP)
100% 5140
83.3 IPS
 
Image Segmentation (Q)
99% 8722
141.4 IPS
 
Pose Estimation (SP)
100% 11126
13.0 IPS
 
Pose Estimation (HP)
100% 92836
108.3 IPS
 
Pose Estimation (Q)
95% 88100
103.3 IPS
 
Object Detection (SP)
100% 1246
98.9 IPS
 
Object Detection (HP)
99% 9336
742.7 IPS
 
Object Detection (Q)
93% 10124
807.8 IPS
 
Face Detection (SP)
100% 2147
25.5 IPS
 
Face Detection (HP)
100% 11940
141.9 IPS
 
Face Detection (Q)
100% 13851
164.6 IPS
 
Depth Estimation (SP)
100% 3806
29.3 IPS
 
Depth Estimation (HP)
99% 56136
432.5 IPS
 
Depth Estimation (Q)
85% 68069
531.9 IPS
 
Style Transfer (SP)
100% 13242
17.0 IPS
 
Style Transfer (HP)
100% 146038
187.7 IPS
 
Style Transfer (Q)
95% 134273
173.4 IPS
 
Image Super-Resolution (SP)
100% 2503
92.4 IPS
 
Image Super-Resolution (HP)
100% 20869
770.6 IPS
 
Image Super-Resolution (Q)
99% 27720
1.02 KIPS
 
Text Classification (SP)
100% 847
1.13 KIPS
 
Text Classification (HP)
100% 3847
5.13 KIPS
 
Text Classification (Q)
93% 3857
5.18 KIPS
 
Machine Translation (SP)
100% 1970
33.9 IPS
 
Machine Translation (HP)
100% 2029
34.9 IPS
 
Machine Translation (Q)
98% 2028
35.0 IPS
 

Compare

Set Baseline Geekbench 6 now available