User | ikristof |
Upload Date | February 17 2025 09:41 AM |
Views | 15 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 Max |
System Information | |
---|---|
Operating System | macOS 15.3.1 (Build 24D70) |
Model | MacBook Pro (14-inch, 2024) |
Model ID | Mac16,6 |
Motherboard | Mac16,6 |
CPU Information | |
---|---|
Name | Apple M4 Max |
Topology | 1 Processor, 14 Cores |
Identifier | Apple M4 Max |
Base Frequency | 4.40 GHz |
Cluster 1 | 10 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 36.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2096
389.7 IPS |
|
Image Classification (HP)
|
100% |
16567
3.08 KIPS |
|
Image Classification (Q)
|
97% |
22305
4.16 KIPS |
|
Image Segmentation (SP)
|
100% |
2537
41.1 IPS |
|
Image Segmentation (HP)
|
100% |
23347
378.5 IPS |
|
Image Segmentation (Q)
|
99% |
32697
530.0 IPS |
|
Pose Estimation (SP)
|
100% |
18960
22.1 IPS |
|
Pose Estimation (HP)
|
100% |
123133
143.7 IPS |
|
Pose Estimation (Q)
|
95% |
229246
268.7 IPS |
|
Object Detection (SP)
|
100% |
2582
204.8 IPS |
|
Object Detection (HP)
|
100% |
20672
1.64 KIPS |
|
Object Detection (Q)
|
91% |
25752
2.06 KIPS |
|
Face Detection (SP)
|
100% |
4623
54.9 IPS |
|
Face Detection (HP)
|
100% |
44331
526.8 IPS |
|
Face Detection (Q)
|
100% |
63354
752.8 IPS |
|
Depth Estimation (SP)
|
100% |
9148
70.5 IPS |
|
Depth Estimation (HP)
|
99% |
110627
852.3 IPS |
|
Depth Estimation (Q)
|
85% |
179481
1.40 KIPS |
|
Style Transfer (SP)
|
100% |
36683
47.2 IPS |
|
Style Transfer (HP)
|
100% |
233224
299.8 IPS |
|
Style Transfer (Q)
|
96% |
296474
382.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
7170
264.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
46456
1.72 KIPS |
|
Image Super-Resolution (Q)
|
99% |
76785
2.84 KIPS |
|
Text Classification (SP)
|
100% |
2954
3.94 KIPS |
|
Text Classification (HP)
|
100% |
4784
6.39 KIPS |
|
Text Classification (Q)
|
93% |
5966
8.01 KIPS |
|
Machine Translation (SP)
|
100% |
6108
105.2 IPS |
|
Machine Translation (HP)
|
100% |
17075
294.1 IPS |
|
Machine Translation (Q)
|
98% |
16710
288.8 IPS |