User | tntoak |
Upload Date | August 18 2024 07:33 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B5024e) |
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 | 3.47 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6274
1.17 KIPS |
|
Image Classification (HP)
|
100% |
6456
1.20 KIPS |
|
Image Classification (Q)
|
99% |
5789
1.08 KIPS |
|
Image Segmentation (SP)
|
100% |
11356
184.1 IPS |
|
Image Segmentation (HP)
|
100% |
10750
174.3 IPS |
|
Image Segmentation (Q)
|
100% |
10540
170.9 IPS |
|
Pose Estimation (SP)
|
100% |
62087
72.4 IPS |
|
Pose Estimation (HP)
|
100% |
64983
75.8 IPS |
|
Pose Estimation (Q)
|
97% |
57300
67.1 IPS |
|
Object Detection (SP)
|
100% |
5829
462.4 IPS |
|
Object Detection (HP)
|
100% |
6375
505.7 IPS |
|
Object Detection (Q)
|
91% |
5274
421.5 IPS |
|
Face Detection (SP)
|
100% |
25214
299.6 IPS |
|
Face Detection (HP)
|
100% |
25381
301.6 IPS |
|
Face Detection (Q)
|
100% |
18094
215.0 IPS |
|
Depth Estimation (SP)
|
100% |
29125
224.4 IPS |
|
Depth Estimation (HP)
|
99% |
30528
235.2 IPS |
|
Depth Estimation (Q)
|
97% |
6059
46.8 IPS |
|
Style Transfer (SP)
|
100% |
114206
146.8 IPS |
|
Style Transfer (HP)
|
100% |
128878
165.7 IPS |
|
Style Transfer (Q)
|
100% |
126646
162.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
19880
734.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
20485
756.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
15078
558.6 IPS |
|
Text Classification (SP)
|
100% |
2275
3.04 KIPS |
|
Text Classification (HP)
|
100% |
3876
5.17 KIPS |
|
Text Classification (Q)
|
93% |
3890
5.22 KIPS |
|
Machine Translation (SP)
|
100% |
1058
18.2 IPS |
|
Machine Translation (HP)
|
100% |
1111
19.1 IPS |
|
Machine Translation (Q)
|
98% |
1351
23.3 IPS |