User | Tycho |
Upload Date | August 21 2024 10:32 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Max |
System Information | |
---|---|
Operating System | macOS 15.0 (Build 24A5320a) |
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 | 4.05 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1506
280.1 IPS |
|
Image Classification (HP)
|
100% |
15883
2.95 KIPS |
|
Image Classification (Q)
|
99% |
16734
3.12 KIPS |
|
Image Segmentation (SP)
|
100% |
1847
29.9 IPS |
|
Image Segmentation (HP)
|
100% |
13769
223.2 IPS |
|
Image Segmentation (Q)
|
100% |
13753
222.9 IPS |
|
Pose Estimation (SP)
|
100% |
16648
19.4 IPS |
|
Pose Estimation (HP)
|
100% |
116224
135.6 IPS |
|
Pose Estimation (Q)
|
94% |
113321
132.9 IPS |
|
Object Detection (SP)
|
100% |
1956
155.2 IPS |
|
Object Detection (HP)
|
100% |
15549
1.23 KIPS |
|
Object Detection (Q)
|
91% |
17360
1.39 KIPS |
|
Face Detection (SP)
|
100% |
4031
47.9 IPS |
|
Face Detection (HP)
|
100% |
24547
291.7 IPS |
|
Face Detection (Q)
|
100% |
38225
454.2 IPS |
|
Depth Estimation (SP)
|
100% |
7332
56.5 IPS |
|
Depth Estimation (HP)
|
99% |
85194
656.4 IPS |
|
Depth Estimation (Q)
|
97% |
87018
672.8 IPS |
|
Style Transfer (SP)
|
100% |
30542
39.3 IPS |
|
Style Transfer (HP)
|
100% |
162694
209.1 IPS |
|
Style Transfer (Q)
|
100% |
162919
209.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5710
210.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
39809
1.47 KIPS |
|
Image Super-Resolution (Q)
|
98% |
51160
1.90 KIPS |
|
Text Classification (SP)
|
100% |
2740
3.66 KIPS |
|
Text Classification (HP)
|
100% |
4813
6.42 KIPS |
|
Text Classification (Q)
|
93% |
4740
6.36 KIPS |
|
Machine Translation (SP)
|
100% |
4805
82.8 IPS |
|
Machine Translation (HP)
|
100% |
2710
46.7 IPS |
|
Machine Translation (Q)
|
98% |
2707
46.8 IPS |