Geekbench AI Score

4716
Single Precision Score
36869
Half Precision Score
52062
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User Martythebrit
Upload Date January 25 2025 04:45 PM
Views 18

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% 2042
379.8 IPS
 
Image Classification (HP)
100% 17235
3.21 KIPS
 
Image Classification (Q)
97% 27560
5.14 KIPS
 
Image Segmentation (SP)
100% 2065
33.5 IPS
 
Image Segmentation (HP)
100% 21909
355.2 IPS
 
Image Segmentation (Q)
99% 30077
487.6 IPS
 
Pose Estimation (SP)
100% 10033
11.7 IPS
 
Pose Estimation (HP)
100% 123861
144.5 IPS
 
Pose Estimation (Q)
95% 232543
272.6 IPS
 
Object Detection (SP)
100% 2284
181.1 IPS
 
Object Detection (HP)
100% 18694
1.48 KIPS
 
Object Detection (Q)
91% 26220
2.10 KIPS
 
Face Detection (SP)
100% 3954
47.0 IPS
 
Face Detection (HP)
100% 43466
516.5 IPS
 
Face Detection (Q)
100% 55886
664.1 IPS
 
Depth Estimation (SP)
100% 8351
64.3 IPS
 
Depth Estimation (HP)
99% 99308
765.1 IPS
 
Depth Estimation (Q)
85% 173056
1.35 KIPS
 
Style Transfer (SP)
100% 25338
32.6 IPS
 
Style Transfer (HP)
100% 233484
300.1 IPS
 
Style Transfer (Q)
96% 298979
385.8 IPS
 
Image Super-Resolution (SP)
100% 5783
213.5 IPS
 
Image Super-Resolution (HP)
100% 49455
1.83 KIPS
 
Image Super-Resolution (Q)
99% 86624
3.20 KIPS
 
Text Classification (SP)
100% 2976
3.97 KIPS
 
Text Classification (HP)
100% 6476
8.64 KIPS
 
Text Classification (Q)
93% 6151
8.25 KIPS
 
Machine Translation (SP)
100% 3918
67.5 IPS
 
Machine Translation (HP)
100% 16446
283.3 IPS
 
Machine Translation (Q)
98% 18788
324.7 IPS
 

Compare

Set Baseline Geekbench 6 now available