User | ChrisCalderon |
Upload Date | January 13 2025 10:14 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.2 (Build 24C101) |
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 | 4.51 GHz |
Cluster 1 | 12 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 128.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
10350
1.92 KIPS |
|
Image Classification (HP)
|
100% |
10597
1.97 KIPS |
|
Image Classification (Q)
|
97% |
9176
1.71 KIPS |
|
Image Segmentation (SP)
|
100% |
19520
316.4 IPS |
|
Image Segmentation (HP)
|
100% |
20526
332.7 IPS |
|
Image Segmentation (Q)
|
99% |
21134
342.6 IPS |
|
Pose Estimation (SP)
|
100% |
107237
125.1 IPS |
|
Pose Estimation (HP)
|
100% |
110313
128.7 IPS |
|
Pose Estimation (Q)
|
95% |
104088
122.0 IPS |
|
Object Detection (SP)
|
100% |
9265
734.9 IPS |
|
Object Detection (HP)
|
100% |
10235
811.9 IPS |
|
Object Detection (Q)
|
91% |
8808
703.9 IPS |
|
Face Detection (SP)
|
100% |
39523
469.6 IPS |
|
Face Detection (HP)
|
100% |
42845
509.1 IPS |
|
Face Detection (Q)
|
100% |
32051
380.8 IPS |
|
Depth Estimation (SP)
|
100% |
44761
344.9 IPS |
|
Depth Estimation (HP)
|
99% |
47016
362.2 IPS |
|
Depth Estimation (Q)
|
85% |
40300
315.0 IPS |
|
Style Transfer (SP)
|
100% |
220469
283.4 IPS |
|
Style Transfer (HP)
|
100% |
239437
307.8 IPS |
|
Style Transfer (Q)
|
96% |
220219
284.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
30517
1.13 KIPS |
|
Image Super-Resolution (HP)
|
100% |
32506
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
26696
985.8 IPS |
|
Text Classification (SP)
|
100% |
2984
3.98 KIPS |
|
Text Classification (HP)
|
100% |
5421
7.24 KIPS |
|
Text Classification (Q)
|
93% |
5408
7.26 KIPS |
|
Machine Translation (SP)
|
100% |
3609
62.2 IPS |
|
Machine Translation (HP)
|
100% |
2099
36.1 IPS |
|
Machine Translation (Q)
|
98% |
3584
61.9 IPS |