User | zensage42 |
Upload Date | December 23 2024 04:49 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D5034f) |
Model | MacBook Pro (16-inch, 2024) |
Model ID | Mac16,5 |
Motherboard | Mac16,5 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 16 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.04 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2066
384.2 IPS |
|
Image Classification (HP)
|
100% |
18490
3.44 KIPS |
|
Image Classification (Q)
|
97% |
23900
4.46 KIPS |
|
Image Segmentation (SP)
|
100% |
2346
38.0 IPS |
|
Image Segmentation (HP)
|
100% |
23204
376.1 IPS |
|
Image Segmentation (Q)
|
99% |
32293
523.5 IPS |
|
Pose Estimation (SP)
|
100% |
18176
21.2 IPS |
|
Pose Estimation (HP)
|
100% |
123979
144.7 IPS |
|
Pose Estimation (Q)
|
95% |
232741
272.8 IPS |
|
Object Detection (SP)
|
100% |
2407
190.9 IPS |
|
Object Detection (HP)
|
100% |
21106
1.67 KIPS |
|
Object Detection (Q)
|
91% |
25210
2.01 KIPS |
|
Face Detection (SP)
|
100% |
4334
51.5 IPS |
|
Face Detection (HP)
|
100% |
44507
528.8 IPS |
|
Face Detection (Q)
|
100% |
64432
765.6 IPS |
|
Depth Estimation (SP)
|
100% |
8709
67.1 IPS |
|
Depth Estimation (HP)
|
99% |
108065
832.6 IPS |
|
Depth Estimation (Q)
|
85% |
175283
1.37 KIPS |
|
Style Transfer (SP)
|
100% |
36297
46.7 IPS |
|
Style Transfer (HP)
|
100% |
233797
300.5 IPS |
|
Style Transfer (Q)
|
96% |
299473
386.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
7119
262.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
46422
1.71 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82121
3.03 KIPS |
|
Text Classification (SP)
|
100% |
2935
3.92 KIPS |
|
Text Classification (HP)
|
100% |
5542
7.40 KIPS |
|
Text Classification (Q)
|
93% |
5662
7.60 KIPS |
|
Machine Translation (SP)
|
100% |
5783
99.6 IPS |
|
Machine Translation (HP)
|
100% |
16699
287.6 IPS |
|
Machine Translation (Q)
|
98% |
16677
288.2 IPS |