User | danb |
Upload Date | October 28 2024 11:07 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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% |
8524
1.59 KIPS |
|
Image Classification (HP)
|
100% |
8875
1.65 KIPS |
|
Image Classification (Q)
|
97% |
7458
1.39 KIPS |
|
Image Segmentation (SP)
|
100% |
16939
274.6 IPS |
|
Image Segmentation (HP)
|
100% |
17656
286.2 IPS |
|
Image Segmentation (Q)
|
99% |
18427
298.7 IPS |
|
Pose Estimation (SP)
|
100% |
92612
108.1 IPS |
|
Pose Estimation (HP)
|
100% |
95836
111.8 IPS |
|
Pose Estimation (Q)
|
95% |
90153
105.7 IPS |
|
Object Detection (SP)
|
100% |
7954
630.9 IPS |
|
Object Detection (HP)
|
100% |
8621
683.8 IPS |
|
Object Detection (Q)
|
91% |
7451
595.4 IPS |
|
Face Detection (SP)
|
100% |
32986
391.9 IPS |
|
Face Detection (HP)
|
100% |
37067
440.4 IPS |
|
Face Detection (Q)
|
100% |
27814
330.5 IPS |
|
Depth Estimation (SP)
|
100% |
38723
298.3 IPS |
|
Depth Estimation (HP)
|
99% |
41655
320.9 IPS |
|
Depth Estimation (Q)
|
85% |
34177
267.1 IPS |
|
Style Transfer (SP)
|
100% |
187849
241.5 IPS |
|
Style Transfer (HP)
|
100% |
206953
266.0 IPS |
|
Style Transfer (Q)
|
96% |
190862
246.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
25632
946.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
26876
992.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
21851
806.8 IPS |
|
Text Classification (SP)
|
100% |
2786
3.72 KIPS |
|
Text Classification (HP)
|
100% |
4960
6.62 KIPS |
|
Text Classification (Q)
|
93% |
4949
6.64 KIPS |
|
Machine Translation (SP)
|
100% |
2776
47.8 IPS |
|
Machine Translation (HP)
|
100% |
2991
51.5 IPS |
|
Machine Translation (Q)
|
98% |
2472
42.7 IPS |