User | anthonynelzin |
Upload Date | March 13 2025 09:40 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.3.2 (Build 24D2082) |
Model | Mac16,9 |
Model ID | Mac16,9 |
Motherboard | Mac16,9 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2137
397.5 IPS |
|
Image Classification (HP)
|
100% |
16808
3.13 KIPS |
|
Image Classification (Q)
|
97% |
21370
3.99 KIPS |
|
Image Segmentation (SP)
|
100% |
2563
41.5 IPS |
|
Image Segmentation (HP)
|
100% |
22611
366.5 IPS |
|
Image Segmentation (Q)
|
99% |
31161
505.1 IPS |
|
Pose Estimation (SP)
|
100% |
19207
22.4 IPS |
|
Pose Estimation (HP)
|
100% |
123109
143.6 IPS |
|
Pose Estimation (Q)
|
95% |
231253
271.0 IPS |
|
Object Detection (SP)
|
100% |
2596
205.9 IPS |
|
Object Detection (HP)
|
100% |
18857
1.50 KIPS |
|
Object Detection (Q)
|
91% |
22963
1.83 KIPS |
|
Face Detection (SP)
|
100% |
4834
57.4 IPS |
|
Face Detection (HP)
|
100% |
44036
523.2 IPS |
|
Face Detection (Q)
|
100% |
63587
755.6 IPS |
|
Depth Estimation (SP)
|
100% |
9138
70.4 IPS |
|
Depth Estimation (HP)
|
99% |
103502
797.4 IPS |
|
Depth Estimation (Q)
|
85% |
175141
1.37 KIPS |
|
Style Transfer (SP)
|
100% |
36746
47.2 IPS |
|
Style Transfer (HP)
|
100% |
232635
299.1 IPS |
|
Style Transfer (Q)
|
96% |
289853
374.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
7218
266.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
44862
1.66 KIPS |
|
Image Super-Resolution (Q)
|
99% |
75518
2.79 KIPS |
|
Text Classification (SP)
|
100% |
2944
3.93 KIPS |
|
Text Classification (HP)
|
100% |
5092
6.80 KIPS |
|
Text Classification (Q)
|
93% |
5083
6.82 KIPS |
|
Machine Translation (SP)
|
100% |
6160
106.1 IPS |
|
Machine Translation (HP)
|
100% |
15979
275.2 IPS |
|
Machine Translation (Q)
|
98% |
16045
277.3 IPS |