Geekbench ML Score

8572
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User seanzxx
Upload Date July 02 2024 09:34 AM
Views 29

System Information

System Information
Operating System macOS 15.0 (Build 24A5279h)
Model MacBook Pro (16-inch, 2021)
Model IDMacBookPro18,2
Motherboard MacBookPro18,2
CPU Information
Name Apple M1 Max
Topology 1 Processor, 10 Cores
Identifier Apple M1 Max
Base Frequency 3.22 GHz
Cluster 18 Cores
Cluster 22 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 64.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4511
844.1 IPS
 
Image Classification (F16)
100% 6739
1.26 KIPS
 
Image Classification (I8)
99% 6863
1.28 KIPS
 
Image Segmentation (F32)
100% 1552
25.9 IPS
 
Image Segmentation (F16)
100% 1393
23.3 IPS
 
Image Segmentation (I8)
100% 1445
24.1 IPS
 
Pose Estimation (F32)
100% 52733
63.9 IPS
 
Pose Estimation (F16)
100% 62217
75.3 IPS
 
Pose Estimation (I8)
100% 62186
75.3 IPS
 
Object Detection (F32)
100% 3526
263.2 IPS
 
Object Detection (F16)
100% 4532
338.3 IPS
 
Object Detection (I8)
97% 3279
244.8 IPS
 
Face Detection (F32)
100% 15317
182.1 IPS
 
Face Detection (F16)
97% 10704
127.3 IPS
 
Face Detection (I8)
96% 11223
133.4 IPS
 
Depth Estimation (F32)
100% 25360
196.7 IPS
 
Depth Estimation (F16)
100% 27170
210.7 IPS
 
Depth Estimation (I8)
37% 30504
236.6 IPS
 
Style Transfer (F32)
100% 85328
112.2 IPS
 
Style Transfer (F16)
100% 112095
147.5 IPS
 
Style Transfer (I8)
100% 115740
152.2 IPS
 
Image Super-Resolution (F32)
100% 8685
310.2 IPS
 
Image Super-Resolution (F16)
100% 14450
516.1 IPS
 
Image Super-Resolution (I8)
100% 15382
549.4 IPS
 
Text Classification (F32)
100% 2087
3.00 KIPS
 
Text Classification (F16)
100% 3512
5.05 KIPS
 
Text Classification (I8)
96% 3443
4.95 KIPS
 
Machine Translation (F32)
100% 897
16.5 IPS
 
Machine Translation (F16)
100% 970
17.9 IPS
 
Machine Translation (I8)
99% 779
14.3 IPS
 

Compare

Set Baseline Geekbench 6 now available