User | gpt |
Upload Date | September 10 2025 09:01 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.6.1 (Build 24G90) |
Model | MacBook Pro (14-inch, Nov 2023) |
Model ID | Mac15,8 |
Motherboard | Mac15,8 |
CPU Information | |
---|---|
Name | Apple M3 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M3 Max |
Base Frequency | 3.80 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1530
284.6 IPS |
|
Image Classification (HP)
|
100% |
16776
3.12 KIPS |
|
Image Classification (Q)
|
97% |
18454
3.44 KIPS |
|
Image Segmentation (SP)
|
100% |
1845
29.9 IPS |
|
Image Segmentation (HP)
|
100% |
22359
362.5 IPS |
|
Image Segmentation (Q)
|
99% |
27720
449.4 IPS |
|
Pose Estimation (SP)
|
100% |
16567
19.3 IPS |
|
Pose Estimation (HP)
|
100% |
120782
140.9 IPS |
|
Pose Estimation (Q)
|
95% |
119856
140.5 IPS |
|
Object Detection (SP)
|
100% |
1937
153.7 IPS |
|
Object Detection (HP)
|
100% |
19576
1.55 KIPS |
|
Object Detection (Q)
|
91% |
19903
1.59 KIPS |
|
Face Detection (SP)
|
100% |
4014
47.7 IPS |
|
Face Detection (HP)
|
100% |
38608
458.7 IPS |
|
Face Detection (Q)
|
100% |
50073
595.0 IPS |
|
Depth Estimation (SP)
|
100% |
7156
55.1 IPS |
|
Depth Estimation (HP)
|
99% |
106370
819.5 IPS |
|
Depth Estimation (Q)
|
85% |
122480
957.6 IPS |
|
Style Transfer (SP)
|
100% |
30294
38.9 IPS |
|
Style Transfer (HP)
|
100% |
221884
285.2 IPS |
|
Style Transfer (Q)
|
96% |
213095
275.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5893
217.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
42887
1.58 KIPS |
|
Image Super-Resolution (Q)
|
99% |
52248
1.93 KIPS |
|
Text Classification (SP)
|
100% |
3097
4.13 KIPS |
|
Text Classification (HP)
|
100% |
5071
6.77 KIPS |
|
Text Classification (Q)
|
93% |
5210
6.99 KIPS |
|
Machine Translation (SP)
|
100% |
4770
82.2 IPS |
|
Machine Translation (HP)
|
100% |
4843
83.4 IPS |
|
Machine Translation (Q)
|
98% |
5192
89.7 IPS |