Geekbench AI Score

4702
Single Precision Score
37228
Half Precision Score
51563
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

User Martythebrit
Upload Date March 23 2025 09:59 PM
Views 17

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4
System Information
Operating System macOS 15.3.2 (Build 24D81)
Model Mac mini (2024)
Model IDMac16,10
Motherboard Mac16,10
CPU Information
Name Apple M4
Topology 1 Processor, 10 Cores
Identifier Apple M4
Base Frequency 4.41 GHz
Cluster 14 Cores
Cluster 26 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2022
376.1 IPS
 
Image Classification (HP)
100% 18323
3.41 KIPS
 
Image Classification (Q)
97% 24992
4.66 KIPS
 
Image Segmentation (SP)
100% 2054
33.3 IPS
 
Image Segmentation (HP)
100% 21725
352.2 IPS
 
Image Segmentation (Q)
99% 30032
486.8 IPS
 
Pose Estimation (SP)
100% 10043
11.7 IPS
 
Pose Estimation (HP)
100% 123828
144.5 IPS
 
Pose Estimation (Q)
95% 232879
272.9 IPS
 
Object Detection (SP)
100% 2283
181.1 IPS
 
Object Detection (HP)
100% 18617
1.48 KIPS
 
Object Detection (Q)
91% 26465
2.11 KIPS
 
Face Detection (SP)
100% 3933
46.7 IPS
 
Face Detection (HP)
100% 44219
525.4 IPS
 
Face Detection (Q)
100% 63039
749.0 IPS
 
Depth Estimation (SP)
100% 8314
64.1 IPS
 
Depth Estimation (HP)
99% 100065
770.9 IPS
 
Depth Estimation (Q)
85% 170758
1.34 KIPS
 
Style Transfer (SP)
100% 25303
32.5 IPS
 
Style Transfer (HP)
100% 234043
300.9 IPS
 
Style Transfer (Q)
96% 301001
388.4 IPS
 
Image Super-Resolution (SP)
100% 5850
216.0 IPS
 
Image Super-Resolution (HP)
100% 51172
1.89 KIPS
 
Image Super-Resolution (Q)
99% 85941
3.17 KIPS
 
Text Classification (SP)
100% 2948
3.93 KIPS
 
Text Classification (HP)
100% 6385
8.52 KIPS
 
Text Classification (Q)
93% 5645
7.58 KIPS
 
Machine Translation (SP)
100% 3890
67.0 IPS
 
Machine Translation (HP)
100% 16470
283.7 IPS
 
Machine Translation (Q)
98% 18273
315.8 IPS
 

Compare

Set Baseline Geekbench 6 now available