User | JoshuaChung |
Upload Date | March 08 2025 02:44 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,11 |
Motherboard | Mac15,11 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M3 Max |
Base Frequency | 4.05 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
7745
1.44 KIPS |
|
Image Classification (HP)
|
100% |
8137
1.51 KIPS |
|
Image Classification (Q)
|
99% |
8078
1.51 KIPS |
|
Image Segmentation (SP)
|
100% |
14312
232.0 IPS |
|
Image Segmentation (HP)
|
100% |
15222
246.8 IPS |
|
Image Segmentation (Q)
|
100% |
15193
246.3 IPS |
|
Pose Estimation (SP)
|
100% |
67683
79.0 IPS |
|
Pose Estimation (HP)
|
100% |
70807
82.6 IPS |
|
Pose Estimation (Q)
|
97% |
64674
75.7 IPS |
|
Object Detection (SP)
|
100% |
7657
607.3 IPS |
|
Object Detection (HP)
|
100% |
8202
650.6 IPS |
|
Object Detection (Q)
|
91% |
7095
567.0 IPS |
|
Face Detection (SP)
|
100% |
28526
339.0 IPS |
|
Face Detection (HP)
|
100% |
31102
369.6 IPS |
|
Face Detection (Q)
|
100% |
24019
285.4 IPS |
|
Depth Estimation (SP)
|
100% |
34494
265.8 IPS |
|
Depth Estimation (HP)
|
99% |
36342
280.0 IPS |
|
Depth Estimation (Q)
|
97% |
5945
46.0 IPS |
|
Style Transfer (SP)
|
100% |
148017
190.3 IPS |
|
Style Transfer (HP)
|
100% |
164463
211.4 IPS |
|
Style Transfer (Q)
|
100% |
163875
210.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
23175
855.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
23760
877.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
18808
696.8 IPS |
|
Text Classification (SP)
|
100% |
3176
4.24 KIPS |
|
Text Classification (HP)
|
100% |
5408
7.22 KIPS |
|
Text Classification (Q)
|
93% |
5459
7.33 KIPS |
|
Machine Translation (SP)
|
100% |
2146
37.0 IPS |
|
Machine Translation (HP)
|
98% |
7572
130.8 IPS |
|
Machine Translation (Q)
|
98% |
7595
131.2 IPS |