User | Nicktenn |
Upload Date | August 15 2024 05:24 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
Model | Mac Studio (2023) |
Model ID | Mac14,13 |
Motherboard | Mac14,13 |
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% |
6283
1.17 KIPS |
|
Image Classification (HP)
|
100% |
6410
1.19 KIPS |
|
Image Classification (Q)
|
99% |
5743
1.07 KIPS |
|
Image Segmentation (SP)
|
100% |
12073
195.7 IPS |
|
Image Segmentation (HP)
|
100% |
11780
191.0 IPS |
|
Image Segmentation (Q)
|
100% |
11436
185.4 IPS |
|
Pose Estimation (SP)
|
100% |
62137
72.5 IPS |
|
Pose Estimation (HP)
|
100% |
64932
75.8 IPS |
|
Pose Estimation (Q)
|
97% |
57548
67.4 IPS |
|
Object Detection (SP)
|
100% |
6023
477.7 IPS |
|
Object Detection (HP)
|
100% |
6415
508.8 IPS |
|
Object Detection (Q)
|
91% |
5283
422.1 IPS |
|
Face Detection (SP)
|
100% |
25354
301.3 IPS |
|
Face Detection (HP)
|
100% |
25470
302.6 IPS |
|
Face Detection (Q)
|
100% |
18118
215.3 IPS |
|
Depth Estimation (SP)
|
100% |
29347
226.1 IPS |
|
Depth Estimation (HP)
|
99% |
29922
230.5 IPS |
|
Depth Estimation (Q)
|
97% |
6080
47.0 IPS |
|
Style Transfer (SP)
|
100% |
114048
146.6 IPS |
|
Style Transfer (HP)
|
100% |
128339
165.0 IPS |
|
Style Transfer (Q)
|
100% |
127182
163.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
20078
741.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
20591
760.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
15181
562.4 IPS |
|
Text Classification (SP)
|
100% |
2295
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3863
5.16 KIPS |
|
Text Classification (Q)
|
93% |
3868
5.19 KIPS |
|
Machine Translation (SP)
|
100% |
2060
35.5 IPS |
|
Machine Translation (HP)
|
100% |
1954
33.7 IPS |
|
Machine Translation (Q)
|
98% |
2033
35.1 IPS |