User | JoshuaChung |
Upload Date | August 15 2024 05:25 PM |
Views | 11 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,11 |
Motherboard | Mac15,11 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M3 Max |
Base Frequency | 3.76 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1158
215.3 IPS |
|
Image Classification (HP)
|
100% |
7451
1.39 KIPS |
|
Image Classification (Q)
|
99% |
7793
1.45 KIPS |
|
Image Segmentation (SP)
|
100% |
792
12.8 IPS |
|
Image Segmentation (HP)
|
100% |
6440
104.4 IPS |
|
Image Segmentation (Q)
|
100% |
6462
104.8 IPS |
|
Pose Estimation (SP)
|
100% |
15322
17.9 IPS |
|
Pose Estimation (HP)
|
100% |
103309
120.5 IPS |
|
Pose Estimation (Q)
|
94% |
99746
117.0 IPS |
|
Object Detection (SP)
|
100% |
1256
99.6 IPS |
|
Object Detection (HP)
|
100% |
10214
810.2 IPS |
|
Object Detection (Q)
|
93% |
10056
802.4 IPS |
|
Face Detection (SP)
|
100% |
2306
27.4 IPS |
|
Face Detection (HP)
|
100% |
12652
150.3 IPS |
|
Face Detection (Q)
|
100% |
14543
172.8 IPS |
|
Depth Estimation (SP)
|
100% |
4039
31.1 IPS |
|
Depth Estimation (HP)
|
99% |
60764
468.2 IPS |
|
Depth Estimation (Q)
|
97% |
63809
493.4 IPS |
|
Style Transfer (SP)
|
100% |
15617
20.1 IPS |
|
Style Transfer (HP)
|
100% |
149119
191.7 IPS |
|
Style Transfer (Q)
|
100% |
149710
192.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3281
121.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
20111
742.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
24689
914.7 IPS |
|
Text Classification (SP)
|
100% |
1080
1.44 KIPS |
|
Text Classification (HP)
|
100% |
887
1.18 KIPS |
|
Text Classification (Q)
|
93% |
782
1.05 KIPS |
|
Machine Translation (SP)
|
100% |
2214
38.1 IPS |
|
Machine Translation (HP)
|
96% |
2229
38.5 IPS |
|
Machine Translation (Q)
|
98% |
2232
38.6 IPS |