Geekbench AI Score

4743
Single Precision Score
37190
Half Precision Score
51912
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

User jonathanmiranda
Upload Date April 09 2025 03:30 PM
Views 10

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4
System Information
Operating System macOS 15.2 (Build 24C101)
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% 2053
381.9 IPS
 
Image Classification (HP)
100% 18509
3.44 KIPS
 
Image Classification (Q)
97% 25711
4.80 KIPS
 
Image Segmentation (SP)
100% 2139
34.7 IPS
 
Image Segmentation (HP)
100% 22033
357.2 IPS
 
Image Segmentation (Q)
99% 30173
489.1 IPS
 
Pose Estimation (SP)
100% 9955
11.6 IPS
 
Pose Estimation (HP)
100% 123732
144.4 IPS
 
Pose Estimation (Q)
95% 234339
274.7 IPS
 
Object Detection (SP)
100% 2303
182.7 IPS
 
Object Detection (HP)
100% 18608
1.48 KIPS
 
Object Detection (Q)
91% 26034
2.08 KIPS
 
Face Detection (SP)
100% 4062
48.3 IPS
 
Face Detection (HP)
100% 44611
530.1 IPS
 
Face Detection (Q)
100% 56399
670.1 IPS
 
Depth Estimation (SP)
100% 8411
64.8 IPS
 
Depth Estimation (HP)
99% 101030
778.4 IPS
 
Depth Estimation (Q)
85% 172491
1.35 KIPS
 
Style Transfer (SP)
100% 25329
32.6 IPS
 
Style Transfer (HP)
100% 234162
301.0 IPS
 
Style Transfer (Q)
96% 299549
386.6 IPS
 
Image Super-Resolution (SP)
100% 5740
211.9 IPS
 
Image Super-Resolution (HP)
100% 49631
1.83 KIPS
 
Image Super-Resolution (Q)
99% 89532
3.31 KIPS
 
Text Classification (SP)
100% 2954
3.94 KIPS
 
Text Classification (HP)
100% 6258
8.35 KIPS
 
Text Classification (Q)
93% 6239
8.37 KIPS
 
Machine Translation (SP)
100% 3905
67.3 IPS
 
Machine Translation (HP)
100% 16445
283.3 IPS
 
Machine Translation (Q)
98% 18450
318.8 IPS
 

Compare

Set Baseline Geekbench 6 now available