User | Rhein080 |
Upload Date | January 27 2025 06:37 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
Model | MacBook Pro (16-inch, 2023) |
Model ID | Mac14,6 |
Motherboard | Mac14,6 |
CPU Information | |
---|---|
Name | Apple M2 Max |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M2 Max |
Base Frequency | 3.43 GHz |
Cluster 1 | 8 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
5706
1.06 KIPS |
|
Image Classification (HP)
|
100% |
5889
1.10 KIPS |
|
Image Classification (Q)
|
97% |
5193
969.2 IPS |
|
Image Segmentation (SP)
|
100% |
11146
180.7 IPS |
|
Image Segmentation (HP)
|
100% |
11004
178.4 IPS |
|
Image Segmentation (Q)
|
99% |
10929
177.2 IPS |
|
Pose Estimation (SP)
|
100% |
61717
72.0 IPS |
|
Pose Estimation (HP)
|
100% |
64473
75.2 IPS |
|
Pose Estimation (Q)
|
95% |
59572
69.8 IPS |
|
Object Detection (SP)
|
100% |
5871
465.7 IPS |
|
Object Detection (HP)
|
100% |
6116
485.1 IPS |
|
Object Detection (Q)
|
91% |
5322
425.3 IPS |
|
Face Detection (SP)
|
100% |
24800
294.7 IPS |
|
Face Detection (HP)
|
100% |
25355
301.3 IPS |
|
Face Detection (Q)
|
100% |
18831
223.8 IPS |
|
Depth Estimation (SP)
|
100% |
28761
221.6 IPS |
|
Depth Estimation (HP)
|
99% |
29401
226.5 IPS |
|
Depth Estimation (Q)
|
85% |
25020
195.5 IPS |
|
Style Transfer (SP)
|
100% |
114079
146.6 IPS |
|
Style Transfer (HP)
|
100% |
127983
164.5 IPS |
|
Style Transfer (Q)
|
96% |
119483
154.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
19389
716.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
19632
724.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
16408
605.9 IPS |
|
Text Classification (SP)
|
100% |
2321
3.10 KIPS |
|
Text Classification (HP)
|
100% |
3972
5.30 KIPS |
|
Text Classification (Q)
|
93% |
3944
5.29 KIPS |
|
Machine Translation (SP)
|
100% |
1386
23.9 IPS |
|
Machine Translation (HP)
|
100% |
1301
22.4 IPS |
|
Machine Translation (Q)
|
98% |
1443
24.9 IPS |