User | pers1 |
Upload Date | October 12 2024 06:41 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.7 (Build 23H124) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,9 |
Motherboard | Mac15,9 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 3.70 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1177
218.8 IPS |
|
Image Classification (HP)
|
100% |
7495
1.39 KIPS |
|
Image Classification (Q)
|
97% |
7496
1.40 KIPS |
|
Image Segmentation (SP)
|
100% |
798
12.9 IPS |
|
Image Segmentation (HP)
|
100% |
6450
104.6 IPS |
|
Image Segmentation (Q)
|
99% |
12924
209.5 IPS |
|
Pose Estimation (SP)
|
100% |
15412
18.0 IPS |
|
Pose Estimation (HP)
|
100% |
103664
121.0 IPS |
|
Pose Estimation (Q)
|
95% |
101635
119.1 IPS |
|
Object Detection (SP)
|
100% |
1400
111.0 IPS |
|
Object Detection (HP)
|
100% |
10159
805.8 IPS |
|
Object Detection (Q)
|
93% |
10128
808.1 IPS |
|
Face Detection (SP)
|
100% |
2351
27.9 IPS |
|
Face Detection (HP)
|
100% |
12801
152.1 IPS |
|
Face Detection (Q)
|
100% |
15087
179.3 IPS |
|
Depth Estimation (SP)
|
100% |
4473
34.5 IPS |
|
Depth Estimation (HP)
|
99% |
61660
475.1 IPS |
|
Depth Estimation (Q)
|
85% |
71015
555.2 IPS |
|
Style Transfer (SP)
|
100% |
16286
20.9 IPS |
|
Style Transfer (HP)
|
100% |
151153
194.3 IPS |
|
Style Transfer (Q)
|
96% |
142485
183.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3315
122.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
19076
704.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
23277
859.5 IPS |
|
Text Classification (SP)
|
100% |
1037
1.38 KIPS |
|
Text Classification (HP)
|
100% |
4046
5.40 KIPS |
|
Text Classification (Q)
|
93% |
3907
5.24 KIPS |
|
Machine Translation (SP)
|
100% |
1925
33.2 IPS |
|
Machine Translation (HP)
|
100% |
2783
47.9 IPS |
|
Machine Translation (Q)
|
98% |
2770
47.9 IPS |