Geekbench ML Score

10103
Core ML GPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 28 2024 04:06 AM
Views 8
Notes MacBook Pro (16-inch, Nov 2023)/M3 Max 16Core CPU/40Core GPU

System Information

System Information
Operating System macOS 14.4.1 (Build 23E224)
Model MacBook Pro (16-inch, Nov 2023)
Model IDMac15,9
Motherboard Mac15,9
CPU Information
Name Apple M3 Max
Topology 1 Processor, 16 Cores
Identifier Apple M3 Max
Base Frequency 4.05 GHz
Cluster 112 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 48.00 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6796
1.27 KIPS
 
Image Classification (F16)
100% 7018
1.31 KIPS
 
Image Classification (I8)
99% 6666
1.25 KIPS
 
Image Segmentation (F32)
100% 3073
51.3 IPS
 
Image Segmentation (F16)
100% 3124
52.2 IPS
 
Image Segmentation (I8)
100% 3173
53.0 IPS
 
Pose Estimation (F32)
100% 83766
101.4 IPS
 
Pose Estimation (F16)
100% 87466
105.9 IPS
 
Pose Estimation (I8)
100% 83890
101.6 IPS
 
Object Detection (F32)
100% 5069
378.5 IPS
 
Object Detection (F16)
100% 5312
396.6 IPS
 
Object Detection (I8)
97% 5019
374.7 IPS
 
Face Detection (F32)
100% 25016
297.4 IPS
 
Face Detection (F16)
98% 26538
315.5 IPS
 
Face Detection (I8)
97% 25090
298.3 IPS
 
Depth Estimation (F32)
100% 36135
280.2 IPS
 
Depth Estimation (F16)
100% 38130
295.7 IPS
 
Depth Estimation (I8)
37% 36961
286.6 IPS
 
Style Transfer (F32)
100% 156730
206.2 IPS
 
Style Transfer (F16)
100% 171401
225.5 IPS
 
Style Transfer (I8)
100% 166077
218.5 IPS
 
Image Super-Resolution (F32)
100% 9268
331.0 IPS
 
Image Super-Resolution (F16)
100% 10625
379.5 IPS
 
Image Super-Resolution (I8)
100% 9803
350.1 IPS
 
Text Classification (F32)
100% 621
891.8 IPS
 
Text Classification (F16)
100% 825
1.18 KIPS
 
Text Classification (I8)
96% 734
1.06 KIPS
 
Machine Translation (F32)
100% 1092
20.1 IPS
 
Machine Translation (F16)
100% 1098
20.2 IPS
 
Machine Translation (I8)
99% 1027
18.9 IPS
 

Compare

Set Baseline Geekbench 6 now available