User | Vinski |
Upload Date | March 25 2025 10:55 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M1 Max |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D81) |
Model | MacBook Pro (14-inch, 2021) |
Model ID | MacBookPro18,4 |
Motherboard | MacBookPro18,4 |
CPU Information | |
---|---|
Name | Apple M1 Max |
Topology | 1 Processor, 10 Cores |
Identifier | Apple M1 Max |
Base Frequency | 3.22 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 2 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4597
854.9 IPS |
|
Image Classification (HP)
|
100% |
4658
866.3 IPS |
|
Image Classification (Q)
|
97% |
3866
721.5 IPS |
|
Image Segmentation (SP)
|
100% |
8878
143.9 IPS |
|
Image Segmentation (HP)
|
100% |
8773
142.2 IPS |
|
Image Segmentation (Q)
|
99% |
8702
141.1 IPS |
|
Pose Estimation (SP)
|
100% |
47426
55.3 IPS |
|
Pose Estimation (HP)
|
100% |
49766
58.1 IPS |
|
Pose Estimation (Q)
|
95% |
45931
53.8 IPS |
|
Object Detection (SP)
|
100% |
4036
320.1 IPS |
|
Object Detection (HP)
|
100% |
5022
398.4 IPS |
|
Object Detection (Q)
|
91% |
4285
342.4 IPS |
|
Face Detection (SP)
|
100% |
18582
220.8 IPS |
|
Face Detection (HP)
|
100% |
19134
227.4 IPS |
|
Face Detection (Q)
|
100% |
13663
162.3 IPS |
|
Depth Estimation (SP)
|
100% |
23726
182.8 IPS |
|
Depth Estimation (HP)
|
99% |
24676
190.1 IPS |
|
Depth Estimation (Q)
|
85% |
20845
162.9 IPS |
|
Style Transfer (SP)
|
100% |
80257
103.2 IPS |
|
Style Transfer (HP)
|
100% |
95296
122.5 IPS |
|
Style Transfer (Q)
|
96% |
89791
115.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
16206
598.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
16284
601.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
12891
476.0 IPS |
|
Text Classification (SP)
|
100% |
2309
3.08 KIPS |
|
Text Classification (HP)
|
100% |
4028
5.38 KIPS |
|
Text Classification (Q)
|
93% |
3956
5.31 KIPS |
|
Machine Translation (SP)
|
100% |
1095
18.9 IPS |
|
Machine Translation (HP)
|
100% |
735
12.7 IPS |
|
Machine Translation (Q)
|
98% |
703
12.1 IPS |