User | lumisade |
Upload Date | November 15 2024 06:02 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.0.1 (Build 24A348) |
Model | MacBook Pro (16-inch, 2023) |
Model ID | Mac14,6 |
Motherboard | Mac14,6 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.67 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6838
1.27 KIPS |
|
Image Classification (HP)
|
100% |
7096
1.32 KIPS |
|
Image Classification (Q)
|
97% |
5335
995.6 IPS |
|
Image Segmentation (SP)
|
100% |
12309
199.5 IPS |
|
Image Segmentation (HP)
|
100% |
12487
202.4 IPS |
|
Image Segmentation (Q)
|
99% |
12029
195.0 IPS |
|
Pose Estimation (SP)
|
100% |
83815
97.8 IPS |
|
Pose Estimation (HP)
|
100% |
86996
101.5 IPS |
|
Pose Estimation (Q)
|
95% |
78076
91.5 IPS |
|
Object Detection (SP)
|
100% |
6495
515.2 IPS |
|
Object Detection (HP)
|
100% |
6810
540.2 IPS |
|
Object Detection (Q)
|
91% |
5636
450.4 IPS |
|
Face Detection (SP)
|
100% |
28076
333.6 IPS |
|
Face Detection (HP)
|
100% |
29298
348.1 IPS |
|
Face Detection (Q)
|
100% |
20613
244.9 IPS |
|
Depth Estimation (SP)
|
100% |
33504
258.1 IPS |
|
Depth Estimation (HP)
|
99% |
34566
266.3 IPS |
|
Depth Estimation (Q)
|
85% |
29082
227.3 IPS |
|
Style Transfer (SP)
|
100% |
135043
173.6 IPS |
|
Style Transfer (HP)
|
100% |
152535
196.1 IPS |
|
Style Transfer (Q)
|
96% |
142132
183.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
20628
761.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
20716
764.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
16333
603.1 IPS |
|
Text Classification (SP)
|
100% |
2315
3.09 KIPS |
|
Text Classification (HP)
|
100% |
3952
5.27 KIPS |
|
Text Classification (Q)
|
93% |
3955
5.31 KIPS |
|
Machine Translation (SP)
|
100% |
1401
24.1 IPS |
|
Machine Translation (HP)
|
100% |
1881
32.4 IPS |
|
Machine Translation (Q)
|
98% |
1784
30.8 IPS |