User | anthonynelzin |
Upload Date | November 12 2024 10:21 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.1 (Build 24B2083) |
Model | Mac16,6 |
Model ID | Mac16,6 |
Motherboard | Mac16,6 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.50 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2107
391.8 IPS |
|
Image Classification (HP)
|
100% |
17148
3.19 KIPS |
|
Image Classification (Q)
|
97% |
21923
4.09 KIPS |
|
Image Segmentation (SP)
|
100% |
2505
40.6 IPS |
|
Image Segmentation (HP)
|
100% |
22696
367.9 IPS |
|
Image Segmentation (Q)
|
99% |
31170
505.3 IPS |
|
Pose Estimation (SP)
|
100% |
19055
22.2 IPS |
|
Pose Estimation (HP)
|
100% |
123252
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
230043
269.6 IPS |
|
Object Detection (SP)
|
100% |
2556
202.8 IPS |
|
Object Detection (HP)
|
100% |
19695
1.56 KIPS |
|
Object Detection (Q)
|
91% |
23321
1.86 KIPS |
|
Face Detection (SP)
|
100% |
4725
56.1 IPS |
|
Face Detection (HP)
|
100% |
44514
528.9 IPS |
|
Face Detection (Q)
|
100% |
64067
761.3 IPS |
|
Depth Estimation (SP)
|
100% |
9025
69.5 IPS |
|
Depth Estimation (HP)
|
99% |
104280
803.4 IPS |
|
Depth Estimation (Q)
|
85% |
177382
1.39 KIPS |
|
Style Transfer (SP)
|
100% |
35813
46.0 IPS |
|
Style Transfer (HP)
|
100% |
232925
299.4 IPS |
|
Style Transfer (Q)
|
96% |
296433
382.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
7115
262.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
45425
1.68 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77259
2.85 KIPS |
|
Text Classification (SP)
|
100% |
2945
3.93 KIPS |
|
Text Classification (HP)
|
100% |
4938
6.59 KIPS |
|
Text Classification (Q)
|
93% |
5057
6.79 KIPS |
|
Machine Translation (SP)
|
100% |
6021
103.7 IPS |
|
Machine Translation (HP)
|
100% |
15975
275.2 IPS |
|
Machine Translation (Q)
|
98% |
16066
277.6 IPS |