User | wbednarski |
Upload Date | May 10 2025 09:44 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.4.1 (Build 24E263) |
Model | Mac16,9 |
Model ID | Mac16,9 |
Motherboard | Mac16,9 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.51 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 64.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2127
395.6 IPS |
|
Image Classification (HP)
|
100% |
17519
3.26 KIPS |
|
Image Classification (Q)
|
97% |
22597
4.22 KIPS |
|
Image Segmentation (SP)
|
100% |
2420
39.2 IPS |
|
Image Segmentation (HP)
|
100% |
22842
370.3 IPS |
|
Image Segmentation (Q)
|
99% |
32684
529.8 IPS |
|
Pose Estimation (SP)
|
100% |
17898
20.9 IPS |
|
Pose Estimation (HP)
|
100% |
122575
143.0 IPS |
|
Pose Estimation (Q)
|
95% |
228852
268.2 IPS |
|
Object Detection (SP)
|
100% |
2636
209.1 IPS |
|
Object Detection (HP)
|
100% |
19483
1.55 KIPS |
|
Object Detection (Q)
|
91% |
24050
1.92 KIPS |
|
Face Detection (SP)
|
100% |
4872
57.9 IPS |
|
Face Detection (HP)
|
100% |
44090
523.9 IPS |
|
Face Detection (Q)
|
100% |
56630
672.9 IPS |
|
Depth Estimation (SP)
|
100% |
8873
68.4 IPS |
|
Depth Estimation (HP)
|
99% |
109690
845.1 IPS |
|
Depth Estimation (Q)
|
85% |
176875
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
25778
33.1 IPS |
|
Style Transfer (HP)
|
100% |
235080
302.2 IPS |
|
Style Transfer (Q)
|
96% |
296175
382.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
6085
224.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
47010
1.74 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80137
2.96 KIPS |
|
Text Classification (SP)
|
100% |
2953
3.94 KIPS |
|
Text Classification (HP)
|
100% |
6238
8.33 KIPS |
|
Text Classification (Q)
|
93% |
6127
8.22 KIPS |
|
Machine Translation (SP)
|
100% |
6137
105.7 IPS |
|
Machine Translation (HP)
|
100% |
17376
299.3 IPS |
|
Machine Translation (Q)
|
98% |
17240
297.9 IPS |