User | Shougeki |
Upload Date | January 24 2025 12:55 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,8 |
Motherboard | Mac16,8 |
CPU Information | |
---|---|
Name | Apple M4 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M4 Pro |
Base Frequency | 4.51 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 48.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7148
1.33 KIPS |
|
Image Classification (HP)
|
100% |
7704
1.43 KIPS |
|
Image Classification (Q)
|
97% |
6342
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
10662
172.8 IPS |
|
Image Segmentation (HP)
|
100% |
11219
181.9 IPS |
|
Image Segmentation (Q)
|
99% |
11457
185.7 IPS |
|
Pose Estimation (SP)
|
100% |
46328
54.1 IPS |
|
Pose Estimation (HP)
|
100% |
48679
56.8 IPS |
|
Pose Estimation (Q)
|
95% |
46143
54.1 IPS |
|
Object Detection (SP)
|
100% |
6744
534.9 IPS |
|
Object Detection (HP)
|
100% |
7339
582.1 IPS |
|
Object Detection (Q)
|
91% |
6149
491.3 IPS |
|
Face Detection (SP)
|
100% |
23111
274.6 IPS |
|
Face Detection (HP)
|
100% |
24960
296.6 IPS |
|
Face Detection (Q)
|
100% |
17912
212.8 IPS |
|
Depth Estimation (SP)
|
100% |
31661
243.9 IPS |
|
Depth Estimation (HP)
|
99% |
34167
263.2 IPS |
|
Depth Estimation (Q)
|
85% |
28375
221.8 IPS |
|
Style Transfer (SP)
|
100% |
106125
136.4 IPS |
|
Style Transfer (HP)
|
100% |
114803
147.6 IPS |
|
Style Transfer (Q)
|
96% |
107349
138.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
17266
637.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
17923
661.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
14155
522.7 IPS |
|
Text Classification (SP)
|
100% |
2940
3.92 KIPS |
|
Text Classification (HP)
|
100% |
5167
6.90 KIPS |
|
Text Classification (Q)
|
93% |
5124
6.88 KIPS |
|
Machine Translation (SP)
|
100% |
2589
44.6 IPS |
|
Machine Translation (HP)
|
100% |
2250
38.8 IPS |
|
Machine Translation (Q)
|
98% |
2437
42.1 IPS |