User | rothomp3 |
Upload Date | July 30 2025 02:56 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 26.0 (Build 25A5316i) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.44 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1408
261.8 IPS |
|
Image Classification (HP)
|
100% |
14976
2.79 KIPS |
|
Image Classification (Q)
|
96% |
17644
3.29 KIPS |
|
Image Segmentation (SP)
|
100% |
1694
27.5 IPS |
|
Image Segmentation (HP)
|
100% |
20218
327.8 IPS |
|
Image Segmentation (Q)
|
99% |
25022
405.6 IPS |
|
Pose Estimation (SP)
|
100% |
12858
15.0 IPS |
|
Pose Estimation (HP)
|
100% |
106303
124.0 IPS |
|
Pose Estimation (Q)
|
95% |
105395
123.5 IPS |
|
Object Detection (SP)
|
100% |
1707
135.4 IPS |
|
Object Detection (HP)
|
99% |
15850
1.26 KIPS |
|
Object Detection (Q)
|
91% |
18316
1.46 KIPS |
|
Face Detection (SP)
|
100% |
3730
44.3 IPS |
|
Face Detection (HP)
|
100% |
36223
430.4 IPS |
|
Face Detection (Q)
|
100% |
47090
559.5 IPS |
|
Depth Estimation (SP)
|
100% |
6322
48.7 IPS |
|
Depth Estimation (HP)
|
99% |
88328
680.5 IPS |
|
Depth Estimation (Q)
|
85% |
110274
861.7 IPS |
|
Style Transfer (SP)
|
100% |
25700
33.0 IPS |
|
Style Transfer (HP)
|
100% |
204653
263.1 IPS |
|
Style Transfer (Q)
|
96% |
193202
249.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4965
183.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
44329
1.64 KIPS |
|
Image Super-Resolution (Q)
|
99% |
50187
1.85 KIPS |
|
Text Classification (SP)
|
100% |
2447
3.27 KIPS |
|
Text Classification (HP)
|
99% |
4093
5.46 KIPS |
|
Text Classification (Q)
|
93% |
4137
5.55 KIPS |
|
Machine Translation (SP)
|
100% |
4616
79.5 IPS |
|
Machine Translation (HP)
|
100% |
4095
70.5 IPS |
|
Machine Translation (Q)
|
98% |
4306
74.4 IPS |