Geekbench ML Score

9691
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User JoshuaChung
Upload Date August 15 2024 04:55 PM
Views 3

System Information

System Information
Operating System macOS 14.6.1 (Build 23G93)
Model MacBook Pro (16-inch, Nov 2023)
Model IDMac15,11
Motherboard Mac15,11
CPU Information
Name Apple M3 Max
Topology 1 Processor, 14 Cores
Identifier Apple M3 Max
Base Frequency 4.05 GHz
Cluster 110 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 36.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6315
1.18 KIPS
 
Image Classification (F16)
100% 6566
1.23 KIPS
 
Image Classification (I8)
99% 6732
1.26 KIPS
 
Image Segmentation (F32)
100% 2846
47.5 IPS
 
Image Segmentation (F16)
100% 2454
41.0 IPS
 
Image Segmentation (I8)
100% 2516
42.0 IPS
 
Pose Estimation (F32)
100% 62487
75.7 IPS
 
Pose Estimation (F16)
100% 89225
108.0 IPS
 
Pose Estimation (I8)
100% 89236
108.1 IPS
 
Object Detection (F32)
100% 4884
364.6 IPS
 
Object Detection (F16)
100% 4302
321.2 IPS
 
Object Detection (I8)
97% 4771
356.2 IPS
 
Face Detection (F32)
100% 21133
251.3 IPS
 
Face Detection (F16)
97% 12108
144.0 IPS
 
Face Detection (I8)
96% 12068
143.5 IPS
 
Depth Estimation (F32)
100% 30851
239.2 IPS
 
Depth Estimation (F16)
100% 36668
284.4 IPS
 
Depth Estimation (I8)
37% 34305
266.0 IPS
 
Style Transfer (F32)
100% 127526
167.8 IPS
 
Style Transfer (F16)
100% 140465
184.8 IPS
 
Style Transfer (I8)
100% 138621
182.3 IPS
 
Image Super-Resolution (F32)
100% 14099
503.5 IPS
 
Image Super-Resolution (F16)
100% 16835
601.2 IPS
 
Image Super-Resolution (I8)
100% 16535
590.5 IPS
 
Text Classification (F32)
100% 1304
1.87 KIPS
 
Text Classification (F16)
100% 876
1.26 KIPS
 
Text Classification (I8)
96% 723
1.04 KIPS
 
Machine Translation (F32)
100% 1170
21.5 IPS
 
Machine Translation (F16)
99% 1175
21.6 IPS
 
Machine Translation (I8)
99% 1206
22.2 IPS
 

Compare

Set Baseline Geekbench 6 now available