Upload Date | November 17 2024 05:02 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Pro |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,8 |
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% |
6970
1.30 KIPS |
|
Image Classification (HP)
|
100% |
7271
1.35 KIPS |
|
Image Classification (Q)
|
97% |
6316
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
10545
170.9 IPS |
|
Image Segmentation (HP)
|
100% |
11231
182.1 IPS |
|
Image Segmentation (Q)
|
99% |
11270
182.7 IPS |
|
Pose Estimation (SP)
|
100% |
45956
53.6 IPS |
|
Pose Estimation (HP)
|
100% |
48077
56.1 IPS |
|
Pose Estimation (Q)
|
95% |
45684
53.5 IPS |
|
Object Detection (SP)
|
100% |
6673
529.3 IPS |
|
Object Detection (HP)
|
100% |
7149
567.1 IPS |
|
Object Detection (Q)
|
91% |
5897
471.2 IPS |
|
Face Detection (SP)
|
100% |
23099
274.5 IPS |
|
Face Detection (HP)
|
100% |
24529
291.5 IPS |
|
Face Detection (Q)
|
100% |
18438
219.1 IPS |
|
Depth Estimation (SP)
|
100% |
30812
237.4 IPS |
|
Depth Estimation (HP)
|
99% |
32640
251.5 IPS |
|
Depth Estimation (Q)
|
85% |
26861
209.9 IPS |
|
Style Transfer (SP)
|
100% |
104134
133.9 IPS |
|
Style Transfer (HP)
|
100% |
112991
145.3 IPS |
|
Style Transfer (Q)
|
96% |
106705
137.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
16381
604.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
18098
668.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
13811
510.0 IPS |
|
Text Classification (SP)
|
100% |
2922
3.90 KIPS |
|
Text Classification (HP)
|
100% |
5198
6.94 KIPS |
|
Text Classification (Q)
|
93% |
5159
6.92 KIPS |
|
Machine Translation (SP)
|
100% |
2591
44.6 IPS |
|
Machine Translation (HP)
|
100% |
1835
31.6 IPS |
|
Machine Translation (Q)
|
98% |
1208
20.9 IPS |