Geekbench AI Score

21973
Single Precision Score
24340
Half Precision Score
21853
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

Upload Date January 07 2025 09:29 AM
Views 2

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M4 Max
System Information
Operating System macOS 15.2 (Build 24C101)
Model MacBook Pro (14-inch, 2024)
Model IDMac16,6
Motherboard Mac16,6
CPU Information
Name Apple M4 Max
Topology 1 Processor, 16 Cores
Identifier Apple M4 Max
Base Frequency 4.50 GHz
Cluster 112 Cores
Cluster 24 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 10227
1.90 KIPS
 
Image Classification (HP)
100% 10814
2.01 KIPS
 
Image Classification (Q)
97% 8859
1.65 KIPS
 
Image Segmentation (SP)
100% 19770
320.5 IPS
 
Image Segmentation (HP)
100% 20509
332.5 IPS
 
Image Segmentation (Q)
99% 21250
344.5 IPS
 
Pose Estimation (SP)
100% 107422
125.3 IPS
 
Pose Estimation (HP)
100% 110388
128.8 IPS
 
Pose Estimation (Q)
95% 104014
121.9 IPS
 
Object Detection (SP)
100% 9199
729.7 IPS
 
Object Detection (HP)
100% 10227
811.2 IPS
 
Object Detection (Q)
91% 8761
700.0 IPS
 
Face Detection (SP)
100% 39613
470.7 IPS
 
Face Detection (HP)
100% 41479
492.9 IPS
 
Face Detection (Q)
100% 31962
379.8 IPS
 
Depth Estimation (SP)
100% 44586
343.5 IPS
 
Depth Estimation (HP)
99% 47569
366.5 IPS
 
Depth Estimation (Q)
85% 40621
317.5 IPS
 
Style Transfer (SP)
100% 222446
286.0 IPS
 
Style Transfer (HP)
100% 240578
309.3 IPS
 
Style Transfer (Q)
96% 220867
285.0 IPS
 
Image Super-Resolution (SP)
100% 30988
1.14 KIPS
 
Image Super-Resolution (HP)
100% 32069
1.18 KIPS
 
Image Super-Resolution (Q)
99% 26734
987.2 IPS
 
Text Classification (SP)
100% 2997
4.00 KIPS
 
Text Classification (HP)
100% 5329
7.11 KIPS
 
Text Classification (Q)
93% 5300
7.11 KIPS
 
Machine Translation (SP)
100% 3599
62.0 IPS
 
Machine Translation (HP)
100% 3594
61.9 IPS
 
Machine Translation (Q)
98% 3565
61.6 IPS
 

Compare

Set Baseline Geekbench 6 now available