Geekbench ML Score

3479
Core ML CPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 29 2024 08:13 AM
Views 10
Notes Mac Studio (2023)/M2 Max/12Core CPU/30CoreGPU/32GB/512GB SSD

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
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
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1459
273.1 IPS
 
Image Classification (F16)
100% 1821
340.7 IPS
 
Image Classification (I8)
99% 1810
338.6 IPS
 
Image Segmentation (F32)
100% 919
15.3 IPS
 
Image Segmentation (F16)
100% 902
15.1 IPS
 
Image Segmentation (I8)
100% 903
15.1 IPS
 
Pose Estimation (F32)
100% 6062
7.34 IPS
 
Pose Estimation (F16)
100% 14321
17.3 IPS
 
Pose Estimation (I8)
100% 14372
17.4 IPS
 
Object Detection (F32)
100% 1489
111.1 IPS
 
Object Detection (F16)
100% 1999
149.2 IPS
 
Object Detection (I8)
97% 1496
111.7 IPS
 
Face Detection (F32)
100% 2938
34.9 IPS
 
Face Detection (F16)
97% 4277
50.9 IPS
 
Face Detection (I8)
97% 4283
50.9 IPS
 
Depth Estimation (F32)
100% 5457
42.3 IPS
 
Depth Estimation (F16)
100% 8596
66.7 IPS
 
Depth Estimation (I8)
99% 8621
66.9 IPS
 
Style Transfer (F32)
100% 16606
21.8 IPS
 
Style Transfer (F16)
100% 26330
34.6 IPS
 
Style Transfer (I8)
100% 25237
33.2 IPS
 
Image Super-Resolution (F32)
100% 3942
140.8 IPS
 
Image Super-Resolution (F16)
100% 4884
174.4 IPS
 
Image Super-Resolution (I8)
100% 4833
172.6 IPS
 
Text Classification (F32)
100% 2081
2.99 KIPS
 
Text Classification (F16)
100% 3076
4.42 KIPS
 
Text Classification (I8)
96% 3068
4.41 KIPS
 
Machine Translation (F32)
100% 1132
20.8 IPS
 
Machine Translation (F16)
100% 1536
28.3 IPS
 
Machine Translation (I8)
99% 1149
21.1 IPS
 

Compare

Set Baseline Geekbench 6 now available