User | Wolfgang1756 |
Upload Date | December 15 2024 07:23 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (16-inch, 2023) |
Model ID | Mac14,6 |
Motherboard | Mac14,6 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.48 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6588
1.23 KIPS |
|
Image Classification (HP)
|
100% |
6883
1.28 KIPS |
|
Image Classification (Q)
|
97% |
5849
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
11281
182.9 IPS |
|
Image Segmentation (HP)
|
100% |
11325
183.6 IPS |
|
Image Segmentation (Q)
|
99% |
11264
182.6 IPS |
|
Pose Estimation (SP)
|
100% |
62199
72.6 IPS |
|
Pose Estimation (HP)
|
100% |
65211
76.1 IPS |
|
Pose Estimation (Q)
|
95% |
60166
70.5 IPS |
|
Object Detection (SP)
|
100% |
6206
492.3 IPS |
|
Object Detection (HP)
|
100% |
6551
519.6 IPS |
|
Object Detection (Q)
|
91% |
5628
449.7 IPS |
|
Face Detection (SP)
|
100% |
25514
303.2 IPS |
|
Face Detection (HP)
|
100% |
26240
311.8 IPS |
|
Face Detection (Q)
|
100% |
19015
225.9 IPS |
|
Depth Estimation (SP)
|
100% |
29797
229.6 IPS |
|
Depth Estimation (HP)
|
99% |
30104
231.9 IPS |
|
Depth Estimation (Q)
|
85% |
25503
199.3 IPS |
|
Style Transfer (SP)
|
100% |
114404
147.1 IPS |
|
Style Transfer (HP)
|
100% |
129056
165.9 IPS |
|
Style Transfer (Q)
|
96% |
120442
155.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
20608
760.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
21191
782.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
17410
642.9 IPS |
|
Text Classification (SP)
|
100% |
2298
3.07 KIPS |
|
Text Classification (HP)
|
100% |
4026
5.37 KIPS |
|
Text Classification (Q)
|
93% |
3993
5.36 KIPS |
|
Machine Translation (SP)
|
100% |
1784
30.7 IPS |
|
Machine Translation (HP)
|
100% |
1954
33.7 IPS |
|
Machine Translation (Q)
|
98% |
1618
28.0 IPS |