User | anthonynelzin |
Upload Date | November 12 2024 10:39 AM |
Views | 2 |
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 | 4.51 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2106
391.7 IPS |
|
Image Classification (HP)
|
100% |
17717
3.29 KIPS |
|
Image Classification (Q)
|
97% |
21955
4.10 KIPS |
|
Image Segmentation (SP)
|
100% |
2525
40.9 IPS |
|
Image Segmentation (HP)
|
100% |
22586
366.1 IPS |
|
Image Segmentation (Q)
|
99% |
31205
505.9 IPS |
|
Pose Estimation (SP)
|
100% |
19107
22.3 IPS |
|
Pose Estimation (HP)
|
100% |
123272
143.8 IPS |
|
Pose Estimation (Q)
|
95% |
229928
269.5 IPS |
|
Object Detection (SP)
|
100% |
2556
202.7 IPS |
|
Object Detection (HP)
|
100% |
19104
1.52 KIPS |
|
Object Detection (Q)
|
91% |
23798
1.90 KIPS |
|
Face Detection (SP)
|
100% |
4776
56.8 IPS |
|
Face Detection (HP)
|
100% |
44455
528.2 IPS |
|
Face Detection (Q)
|
100% |
64004
760.5 IPS |
|
Depth Estimation (SP)
|
100% |
9002
69.4 IPS |
|
Depth Estimation (HP)
|
99% |
104555
805.5 IPS |
|
Depth Estimation (Q)
|
85% |
176855
1.38 KIPS |
|
Style Transfer (SP)
|
100% |
36365
46.7 IPS |
|
Style Transfer (HP)
|
100% |
232911
299.4 IPS |
|
Style Transfer (Q)
|
96% |
297325
383.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
7116
262.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
45306
1.67 KIPS |
|
Image Super-Resolution (Q)
|
99% |
77683
2.87 KIPS |
|
Text Classification (SP)
|
100% |
2964
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5314
7.09 KIPS |
|
Text Classification (Q)
|
93% |
5349
7.18 KIPS |
|
Machine Translation (SP)
|
100% |
6027
103.8 IPS |
|
Machine Translation (HP)
|
100% |
15941
274.6 IPS |
|
Machine Translation (Q)
|
98% |
15981
276.2 IPS |