User | Qiguanjiachen |
Upload Date | June 11 2025 04:49 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 16.0 (Build 25A5279m) |
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 | 3.29 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 32.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
6183
1.15 KIPS |
|
Image Classification (HP)
|
100% |
6432
1.20 KIPS |
|
Image Classification (Q)
|
96% |
5776
1.08 KIPS |
|
Image Segmentation (SP)
|
100% |
11991
194.4 IPS |
|
Image Segmentation (HP)
|
100% |
12195
197.7 IPS |
|
Image Segmentation (Q)
|
99% |
11714
189.9 IPS |
|
Pose Estimation (SP)
|
100% |
61975
72.3 IPS |
|
Pose Estimation (HP)
|
100% |
65755
76.7 IPS |
|
Pose Estimation (Q)
|
96% |
63412
74.3 IPS |
|
Object Detection (SP)
|
100% |
6047
479.6 IPS |
|
Object Detection (HP)
|
100% |
6213
492.8 IPS |
|
Object Detection (Q)
|
92% |
5769
460.5 IPS |
|
Face Detection (SP)
|
100% |
25195
299.4 IPS |
|
Face Detection (HP)
|
100% |
25955
308.4 IPS |
|
Face Detection (Q)
|
100% |
22416
266.4 IPS |
|
Depth Estimation (SP)
|
100% |
29043
223.8 IPS |
|
Depth Estimation (HP)
|
99% |
29632
228.3 IPS |
|
Depth Estimation (Q)
|
86% |
27698
216.4 IPS |
|
Style Transfer (SP)
|
100% |
113690
146.2 IPS |
|
Style Transfer (HP)
|
100% |
129413
166.4 IPS |
|
Style Transfer (Q)
|
96% |
125542
162.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
19627
724.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
20758
766.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
18201
672.1 IPS |
|
Text Classification (SP)
|
100% |
2395
3.20 KIPS |
|
Text Classification (HP)
|
100% |
3885
5.19 KIPS |
|
Text Classification (Q)
|
93% |
3922
5.26 KIPS |
|
Machine Translation (SP)
|
100% |
2905
50.0 IPS |
|
Machine Translation (HP)
|
100% |
2757
47.5 IPS |
|
Machine Translation (Q)
|
98% |
2140
37.0 IPS |