Upload Date | November 17 2024 09:13 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,5 |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
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 | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2135
397.0 IPS |
|
Image Classification (HP)
|
100% |
17477
3.25 KIPS |
|
Image Classification (Q)
|
97% |
22693
4.23 KIPS |
|
Image Segmentation (SP)
|
100% |
2541
41.2 IPS |
|
Image Segmentation (HP)
|
100% |
22614
366.6 IPS |
|
Image Segmentation (Q)
|
99% |
32185
521.7 IPS |
|
Pose Estimation (SP)
|
100% |
19286
22.5 IPS |
|
Pose Estimation (HP)
|
100% |
123252
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
230832
270.5 IPS |
|
Object Detection (SP)
|
100% |
2598
206.1 IPS |
|
Object Detection (HP)
|
100% |
19906
1.58 KIPS |
|
Object Detection (Q)
|
91% |
23422
1.87 KIPS |
|
Face Detection (SP)
|
100% |
4846
57.6 IPS |
|
Face Detection (HP)
|
100% |
44335
526.8 IPS |
|
Face Detection (Q)
|
100% |
64675
768.5 IPS |
|
Depth Estimation (SP)
|
100% |
9148
70.5 IPS |
|
Depth Estimation (HP)
|
99% |
106256
818.6 IPS |
|
Depth Estimation (Q)
|
85% |
177643
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
37184
47.8 IPS |
|
Style Transfer (HP)
|
100% |
232905
299.4 IPS |
|
Style Transfer (Q)
|
96% |
297187
383.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
7241
267.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
45311
1.67 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76893
2.84 KIPS |
|
Text Classification (SP)
|
100% |
2980
3.98 KIPS |
|
Text Classification (HP)
|
100% |
4934
6.59 KIPS |
|
Text Classification (Q)
|
93% |
4939
6.63 KIPS |
|
Machine Translation (SP)
|
100% |
6172
106.3 IPS |
|
Machine Translation (HP)
|
100% |
16294
280.7 IPS |
|
Machine Translation (Q)
|
98% |
16594
286.8 IPS |