Geekbench ML Score

9720
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User idanbo
Upload Date March 29 2024 08:18 AM
Views 9
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 Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5516
1.03 KIPS
 
Image Classification (F16)
100% 7037
1.32 KIPS
 
Image Classification (I8)
99% 7797
1.46 KIPS
 
Image Segmentation (F32)
100% 2427
40.5 IPS
 
Image Segmentation (F16)
100% 1933
32.3 IPS
 
Image Segmentation (I8)
100% 1936
32.3 IPS
 
Pose Estimation (F32)
100% 56698
68.7 IPS
 
Pose Estimation (F16)
100% 78715
95.3 IPS
 
Pose Estimation (I8)
100% 79460
96.2 IPS
 
Object Detection (F32)
100% 3513
262.3 IPS
 
Object Detection (F16)
100% 4224
315.3 IPS
 
Object Detection (I8)
97% 3868
288.8 IPS
 
Face Detection (F32)
100% 19324
229.8 IPS
 
Face Detection (F16)
97% 10755
127.9 IPS
 
Face Detection (I8)
96% 11091
131.9 IPS
 
Depth Estimation (F32)
100% 26628
206.5 IPS
 
Depth Estimation (F16)
100% 36248
281.1 IPS
 
Depth Estimation (I8)
37% 36292
281.4 IPS
 
Style Transfer (F32)
100% 105467
138.7 IPS
 
Style Transfer (F16)
100% 135689
178.5 IPS
 
Style Transfer (I8)
100% 129096
169.8 IPS
 
Image Super-Resolution (F32)
100% 16047
573.1 IPS
 
Image Super-Resolution (F16)
100% 17946
640.9 IPS
 
Image Super-Resolution (I8)
100% 17868
638.1 IPS
 
Text Classification (F32)
100% 486
698.8 IPS
 
Text Classification (F16)
100% 2681
3.85 KIPS
 
Text Classification (I8)
96% 2450
3.52 KIPS
 
Machine Translation (F32)
100% 1036
19.1 IPS
 
Machine Translation (F16)
100% 2878
53.0 IPS
 
Machine Translation (I8)
99% 1046
19.3 IPS
 

Compare

Set Baseline Geekbench 6 now available