User | danb |
Upload Date | October 30 2024 02:53 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B83) |
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 | 4.05 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1504
279.7 IPS |
|
Image Classification (HP)
|
100% |
16212
3.01 KIPS |
|
Image Classification (Q)
|
97% |
18163
3.39 KIPS |
|
Image Segmentation (SP)
|
100% |
1821
29.5 IPS |
|
Image Segmentation (HP)
|
100% |
21891
354.9 IPS |
|
Image Segmentation (Q)
|
99% |
27034
438.2 IPS |
|
Pose Estimation (SP)
|
100% |
16735
19.5 IPS |
|
Pose Estimation (HP)
|
100% |
120548
140.7 IPS |
|
Pose Estimation (Q)
|
95% |
119142
139.6 IPS |
|
Object Detection (SP)
|
100% |
1987
157.6 IPS |
|
Object Detection (HP)
|
100% |
17753
1.41 KIPS |
|
Object Detection (Q)
|
91% |
18317
1.46 KIPS |
|
Face Detection (SP)
|
100% |
4034
47.9 IPS |
|
Face Detection (HP)
|
100% |
38746
460.4 IPS |
|
Face Detection (Q)
|
100% |
49561
588.9 IPS |
|
Depth Estimation (SP)
|
100% |
7234
55.7 IPS |
|
Depth Estimation (HP)
|
99% |
102161
787.1 IPS |
|
Depth Estimation (Q)
|
85% |
119098
931.2 IPS |
|
Style Transfer (SP)
|
100% |
31032
39.9 IPS |
|
Style Transfer (HP)
|
100% |
220422
283.4 IPS |
|
Style Transfer (Q)
|
96% |
209000
269.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5758
212.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
41668
1.54 KIPS |
|
Image Super-Resolution (Q)
|
99% |
52063
1.92 KIPS |
|
Text Classification (SP)
|
100% |
2738
3.65 KIPS |
|
Text Classification (HP)
|
100% |
5293
7.06 KIPS |
|
Text Classification (Q)
|
93% |
4882
6.55 KIPS |
|
Machine Translation (SP)
|
100% |
4789
82.5 IPS |
|
Machine Translation (HP)
|
100% |
7178
123.6 IPS |
|
Machine Translation (Q)
|
98% |
7596
131.3 IPS |