User | alimomen |
Upload Date | November 11 2024 04:02 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C5073e) |
Model | MacBook Pro (14-inch, 2023) |
Model ID | Mac14,5 |
Motherboard | Mac14,5 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.47 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6236
1.16 KIPS |
|
Image Classification (HP)
|
100% |
6542
1.22 KIPS |
|
Image Classification (Q)
|
97% |
5709
1.07 KIPS |
|
Image Segmentation (SP)
|
100% |
10859
176.0 IPS |
|
Image Segmentation (HP)
|
100% |
10704
173.5 IPS |
|
Image Segmentation (Q)
|
99% |
10779
174.7 IPS |
|
Pose Estimation (SP)
|
100% |
62021
72.4 IPS |
|
Pose Estimation (HP)
|
100% |
64841
75.7 IPS |
|
Pose Estimation (Q)
|
95% |
59907
70.2 IPS |
|
Object Detection (SP)
|
100% |
6002
476.1 IPS |
|
Object Detection (HP)
|
100% |
6437
510.6 IPS |
|
Object Detection (Q)
|
91% |
5598
447.3 IPS |
|
Face Detection (SP)
|
100% |
25337
301.1 IPS |
|
Face Detection (HP)
|
100% |
25515
303.2 IPS |
|
Face Detection (Q)
|
100% |
18970
225.4 IPS |
|
Depth Estimation (SP)
|
100% |
29263
225.5 IPS |
|
Depth Estimation (HP)
|
99% |
30024
231.3 IPS |
|
Depth Estimation (Q)
|
85% |
25260
197.4 IPS |
|
Style Transfer (SP)
|
100% |
114280
146.9 IPS |
|
Style Transfer (HP)
|
100% |
128196
164.8 IPS |
|
Style Transfer (Q)
|
96% |
119658
154.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
20425
754.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
20449
755.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
16960
626.3 IPS |
|
Text Classification (SP)
|
100% |
2249
3.00 KIPS |
|
Text Classification (HP)
|
100% |
3857
5.15 KIPS |
|
Text Classification (Q)
|
93% |
3840
5.15 KIPS |
|
Machine Translation (SP)
|
100% |
1227
21.1 IPS |
|
Machine Translation (HP)
|
100% |
1261
21.7 IPS |
|
Machine Translation (Q)
|
98% |
1275
22.0 IPS |