Geekbench ML Score

4092
Core ML CPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 28 2024 04:03 AM
Views 10
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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1680
314.3 IPS
 
Image Classification (F16)
100% 2001
374.4 IPS
 
Image Classification (I8)
99% 1996
373.6 IPS
 
Image Segmentation (F32)
100% 1064
17.8 IPS
 
Image Segmentation (F16)
100% 1037
17.3 IPS
 
Image Segmentation (I8)
100% 1043
17.4 IPS
 
Pose Estimation (F32)
100% 8361
10.1 IPS
 
Pose Estimation (F16)
100% 16460
19.9 IPS
 
Pose Estimation (I8)
100% 16443
19.9 IPS
 
Object Detection (F32)
100% 1743
130.1 IPS
 
Object Detection (F16)
100% 2311
172.5 IPS
 
Object Detection (I8)
97% 1723
128.6 IPS
 
Face Detection (F32)
100% 3462
41.2 IPS
 
Face Detection (F16)
97% 5001
59.5 IPS
 
Face Detection (I8)
97% 5037
59.9 IPS
 
Depth Estimation (F32)
100% 6738
52.3 IPS
 
Depth Estimation (F16)
100% 9769
75.8 IPS
 
Depth Estimation (I8)
99% 9769
75.8 IPS
 
Style Transfer (F32)
100% 19527
25.7 IPS
 
Style Transfer (F16)
100% 28673
37.7 IPS
 
Style Transfer (I8)
100% 28967
38.1 IPS
 
Image Super-Resolution (F32)
100% 5082
181.5 IPS
 
Image Super-Resolution (F16)
100% 5253
187.6 IPS
 
Image Super-Resolution (I8)
100% 5258
187.8 IPS
 
Text Classification (F32)
100% 2511
3.61 KIPS
 
Text Classification (F16)
100% 4191
6.02 KIPS
 
Text Classification (I8)
96% 4194
6.03 KIPS
 
Machine Translation (F32)
100% 1382
25.4 IPS
 
Machine Translation (F16)
100% 1742
32.1 IPS
 
Machine Translation (I8)
99% 1387
25.5 IPS
 

Compare

Set Baseline Geekbench 6 now available