User | tokris |
Upload Date | March 16 2025 12:29 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.4 (Build 24E5228e) |
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 | 3.67 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1481
275.5 IPS |
|
Image Classification (HP)
|
100% |
14208
2.64 KIPS |
|
Image Classification (Q)
|
96% |
17021
3.18 KIPS |
|
Image Segmentation (SP)
|
100% |
1786
28.9 IPS |
|
Image Segmentation (HP)
|
100% |
19743
320.1 IPS |
|
Image Segmentation (Q)
|
99% |
24738
401.0 IPS |
|
Pose Estimation (SP)
|
100% |
12968
15.1 IPS |
|
Pose Estimation (HP)
|
100% |
105562
123.2 IPS |
|
Pose Estimation (Q)
|
95% |
104394
122.4 IPS |
|
Object Detection (SP)
|
100% |
1773
140.6 IPS |
|
Object Detection (HP)
|
99% |
15916
1.27 KIPS |
|
Object Detection (Q)
|
91% |
17541
1.40 KIPS |
|
Face Detection (SP)
|
100% |
3689
43.8 IPS |
|
Face Detection (HP)
|
100% |
36419
432.7 IPS |
|
Face Detection (Q)
|
100% |
47530
564.8 IPS |
|
Depth Estimation (SP)
|
100% |
6378
49.1 IPS |
|
Depth Estimation (HP)
|
99% |
87935
677.5 IPS |
|
Depth Estimation (Q)
|
85% |
109667
857.0 IPS |
|
Style Transfer (SP)
|
100% |
26333
33.9 IPS |
|
Style Transfer (HP)
|
100% |
203953
262.2 IPS |
|
Style Transfer (Q)
|
96% |
190573
245.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5318
196.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
41419
1.53 KIPS |
|
Image Super-Resolution (Q)
|
99% |
49473
1.83 KIPS |
|
Text Classification (SP)
|
100% |
2341
3.12 KIPS |
|
Text Classification (HP)
|
100% |
4062
5.42 KIPS |
|
Text Classification (Q)
|
93% |
4041
5.42 KIPS |
|
Machine Translation (SP)
|
100% |
4484
77.2 IPS |
|
Machine Translation (HP)
|
100% |
4188
72.1 IPS |
|
Machine Translation (Q)
|
98% |
4371
75.5 IPS |