User | JoshuaChung |
Upload Date | September 23 2024 05:38 AM |
Views | 11 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A335) |
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% |
1500
278.9 IPS |
|
Image Classification (HP)
|
100% |
16619
3.09 KIPS |
|
Image Classification (Q)
|
99% |
16689
3.11 KIPS |
|
Image Segmentation (SP)
|
100% |
1847
29.9 IPS |
|
Image Segmentation (HP)
|
100% |
13781
223.4 IPS |
|
Image Segmentation (Q)
|
100% |
13857
224.6 IPS |
|
Pose Estimation (SP)
|
100% |
16691
19.5 IPS |
|
Pose Estimation (HP)
|
100% |
117557
137.2 IPS |
|
Pose Estimation (Q)
|
94% |
113722
133.4 IPS |
|
Object Detection (SP)
|
100% |
1959
155.4 IPS |
|
Object Detection (HP)
|
100% |
15984
1.27 KIPS |
|
Object Detection (Q)
|
91% |
17398
1.39 KIPS |
|
Face Detection (SP)
|
100% |
4044
48.1 IPS |
|
Face Detection (HP)
|
100% |
24691
293.4 IPS |
|
Face Detection (Q)
|
100% |
37564
446.3 IPS |
|
Depth Estimation (SP)
|
100% |
7395
57.0 IPS |
|
Depth Estimation (HP)
|
99% |
83947
646.8 IPS |
|
Depth Estimation (Q)
|
97% |
87383
675.7 IPS |
|
Style Transfer (SP)
|
100% |
30841
39.6 IPS |
|
Style Transfer (HP)
|
100% |
163221
209.8 IPS |
|
Style Transfer (Q)
|
100% |
163012
209.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5761
212.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
40126
1.48 KIPS |
|
Image Super-Resolution (Q)
|
98% |
51935
1.92 KIPS |
|
Text Classification (SP)
|
100% |
2728
3.64 KIPS |
|
Text Classification (HP)
|
100% |
4788
6.39 KIPS |
|
Text Classification (Q)
|
93% |
4772
6.40 KIPS |
|
Machine Translation (SP)
|
100% |
2160
37.2 IPS |
|
Machine Translation (HP)
|
98% |
6958
120.2 IPS |
|
Machine Translation (Q)
|
98% |
7496
129.5 IPS |