User | edsonchan |
Upload Date | August 16 2024 05:40 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 14.6.1 (Build 23G93) |
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 | 3.65 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6156
1.14 KIPS |
|
Image Classification (HP)
|
100% |
6324
1.18 KIPS |
|
Image Classification (Q)
|
99% |
5665
1.06 KIPS |
|
Image Segmentation (SP)
|
100% |
13172
213.5 IPS |
|
Image Segmentation (HP)
|
100% |
12928
209.6 IPS |
|
Image Segmentation (Q)
|
100% |
12421
201.3 IPS |
|
Pose Estimation (SP)
|
100% |
81636
95.3 IPS |
|
Pose Estimation (HP)
|
100% |
85426
99.7 IPS |
|
Pose Estimation (Q)
|
96% |
75692
88.7 IPS |
|
Object Detection (SP)
|
100% |
5919
469.5 IPS |
|
Object Detection (HP)
|
100% |
6249
495.6 IPS |
|
Object Detection (Q)
|
92% |
5218
416.5 IPS |
|
Face Detection (SP)
|
100% |
23929
284.3 IPS |
|
Face Detection (HP)
|
100% |
24582
292.1 IPS |
|
Face Detection (Q)
|
100% |
17709
210.4 IPS |
|
Depth Estimation (SP)
|
100% |
32354
249.3 IPS |
|
Depth Estimation (HP)
|
99% |
33102
255.0 IPS |
|
Depth Estimation (Q)
|
97% |
33355
257.9 IPS |
|
Style Transfer (SP)
|
100% |
133339
171.4 IPS |
|
Style Transfer (HP)
|
100% |
149811
192.6 IPS |
|
Style Transfer (Q)
|
100% |
147284
189.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
20447
755.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
20780
767.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
15727
582.7 IPS |
|
Text Classification (SP)
|
100% |
1169
1.56 KIPS |
|
Text Classification (HP)
|
100% |
483
645.3 IPS |
|
Text Classification (Q)
|
93% |
519
696.2 IPS |
|
Machine Translation (SP)
|
100% |
2357
40.6 IPS |
|
Machine Translation (HP)
|
100% |
2336
40.2 IPS |
|
Machine Translation (Q)
|
98% |
2327
40.2 IPS |