User | geekgrunt |
Upload Date | April 29 2025 09:03 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | Mac Studio (2023) |
Model ID | Mac14,13 |
Motherboard | Mac14,13 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.35 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1403
260.9 IPS |
|
Image Classification (HP)
|
100% |
15595
2.90 KIPS |
|
Image Classification (Q)
|
96% |
18317
3.42 KIPS |
|
Image Segmentation (SP)
|
100% |
1630
26.4 IPS |
|
Image Segmentation (HP)
|
100% |
19807
321.1 IPS |
|
Image Segmentation (Q)
|
99% |
24859
403.0 IPS |
|
Pose Estimation (SP)
|
100% |
12733
14.9 IPS |
|
Pose Estimation (HP)
|
100% |
106528
124.3 IPS |
|
Pose Estimation (Q)
|
95% |
105661
123.8 IPS |
|
Object Detection (SP)
|
100% |
1671
132.6 IPS |
|
Object Detection (HP)
|
99% |
16110
1.28 KIPS |
|
Object Detection (Q)
|
91% |
18093
1.45 KIPS |
|
Face Detection (SP)
|
100% |
3614
42.9 IPS |
|
Face Detection (HP)
|
100% |
33274
395.4 IPS |
|
Face Detection (Q)
|
100% |
46850
556.7 IPS |
|
Depth Estimation (SP)
|
100% |
6166
47.5 IPS |
|
Depth Estimation (HP)
|
99% |
88705
683.4 IPS |
|
Depth Estimation (Q)
|
85% |
112224
877.0 IPS |
|
Style Transfer (SP)
|
100% |
25229
32.4 IPS |
|
Style Transfer (HP)
|
100% |
205411
264.1 IPS |
|
Style Transfer (Q)
|
96% |
191552
247.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5038
186.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
42930
1.59 KIPS |
|
Image Super-Resolution (Q)
|
99% |
51746
1.91 KIPS |
|
Text Classification (SP)
|
100% |
2372
3.17 KIPS |
|
Text Classification (HP)
|
100% |
4120
5.50 KIPS |
|
Text Classification (Q)
|
93% |
4121
5.53 KIPS |
|
Machine Translation (SP)
|
100% |
4422
76.2 IPS |
|
Machine Translation (HP)
|
100% |
4168
71.8 IPS |
|
Machine Translation (Q)
|
98% |
4348
75.1 IPS |