User | astrokari |
Upload Date | August 31 2024 06:17 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5035e) |
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 | 3.34 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1263
234.9 IPS |
|
Image Classification (HP)
|
100% |
14075
2.62 KIPS |
|
Image Classification (Q)
|
99% |
15532
2.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1743
28.3 IPS |
|
Image Segmentation (HP)
|
100% |
9346
151.5 IPS |
|
Image Segmentation (Q)
|
100% |
9350
151.6 IPS |
|
Pose Estimation (SP)
|
100% |
13038
15.2 IPS |
|
Pose Estimation (HP)
|
100% |
102897
120.1 IPS |
|
Pose Estimation (Q)
|
94% |
97845
114.8 IPS |
|
Object Detection (SP)
|
100% |
1705
135.2 IPS |
|
Object Detection (HP)
|
99% |
14153
1.13 KIPS |
|
Object Detection (Q)
|
91% |
16685
1.33 KIPS |
|
Face Detection (SP)
|
100% |
3705
44.0 IPS |
|
Face Detection (HP)
|
100% |
23735
282.0 IPS |
|
Face Detection (Q)
|
100% |
36552
434.3 IPS |
|
Depth Estimation (SP)
|
100% |
6355
49.0 IPS |
|
Depth Estimation (HP)
|
99% |
74114
571.0 IPS |
|
Depth Estimation (Q)
|
97% |
82463
637.6 IPS |
|
Style Transfer (SP)
|
100% |
25154
32.3 IPS |
|
Style Transfer (HP)
|
100% |
156105
200.7 IPS |
|
Style Transfer (Q)
|
100% |
157291
202.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5163
190.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
40833
1.51 KIPS |
|
Image Super-Resolution (Q)
|
98% |
48550
1.80 KIPS |
|
Text Classification (SP)
|
100% |
2307
3.08 KIPS |
|
Text Classification (HP)
|
100% |
3921
5.23 KIPS |
|
Text Classification (Q)
|
93% |
3894
5.23 KIPS |
|
Machine Translation (SP)
|
100% |
4718
81.3 IPS |
|
Machine Translation (HP)
|
100% |
2084
35.9 IPS |
|
Machine Translation (Q)
|
98% |
2080
35.9 IPS |