Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
marin-community
's Collections
Marin Hero Runs
Delphi
All Marin ISOFlops
DCLM Baseline ISOFlop Models
CommonPile ISOFlop Models
Nemotron ISOFlop Models
Fantastic Optimizers Open-sourced Models
Fantastic Optimizers Open-sourced Models
updated
Mar 2
Best-tuned model for each setting for https://arxiv.org/abs/2509.02046;
Upvote
-
Sort: Collection
OptimizerStudy/adamw_1.2b_1
2B
•
Updated
Oct 23, 2025
•
25
OptimizerStudy/adamw_1.2b_2
2B
•
Updated
Oct 23, 2025
•
8
OptimizerStudy/adamw_1.2b_4
2B
•
Updated
Oct 23, 2025
•
13
OptimizerStudy/adamw_1.2b_8
2B
•
Updated
Oct 23, 2025
•
94
OptimizerStudy/adamw_130m_1
0.3B
•
Updated
Oct 23, 2025
•
17
OptimizerStudy/adamw_130m_16
0.3B
•
Updated
Oct 23, 2025
•
12
OptimizerStudy/adamw_130m_2
0.3B
•
Updated
Oct 23, 2025
•
9
OptimizerStudy/adamw_130m_4
0.3B
•
Updated
Oct 23, 2025
•
19
OptimizerStudy/adamw_130m_8
0.3B
•
Updated
Oct 23, 2025
•
61
OptimizerStudy/adamw_300m_1
0.5B
•
Updated
Oct 23, 2025
•
55
OptimizerStudy/adamw_300m_16
0.5B
•
Updated
Oct 23, 2025
•
6
OptimizerStudy/adamw_300m_2
0.5B
•
Updated
Oct 23, 2025
•
46
OptimizerStudy/adamw_300m_4
0.5B
•
Updated
Oct 23, 2025
•
52
OptimizerStudy/adamw_300m_8
0.5B
•
Updated
Oct 23, 2025
•
924
OptimizerStudy/adamw_520m_1
0.8B
•
Updated
Oct 23, 2025
•
14
OptimizerStudy/adamw_520m_2
0.8B
•
Updated
Oct 23, 2025
•
6
OptimizerStudy/adamw_520m_4
0.8B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/adamw_520m_8
0.8B
•
Updated
Oct 23, 2025
•
366
OptimizerStudy/cautious_130m_1
0.3B
•
Updated
Oct 23, 2025
•
13
OptimizerStudy/cautious_130m_2
0.3B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/cautious_130m_4
0.3B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/cautious_130m_8
0.3B
•
Updated
Oct 23, 2025
•
13
OptimizerStudy/cautious_300m_1
0.5B
•
Updated
Oct 23, 2025
•
9
OptimizerStudy/cautious_300m_2
0.5B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/cautious_300m_4
0.5B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/cautious_300m_8
0.5B
•
Updated
Oct 23, 2025
•
14
OptimizerStudy/cautious_520m_1
0.8B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/cautious_520m_2
0.8B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/cautious_520m_4
0.8B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/cautious_520m_8
0.8B
•
Updated
Oct 23, 2025
•
28
OptimizerStudy/kron_130m_1
0.3B
•
Updated
Oct 23, 2025
•
13
OptimizerStudy/kron_130m_2
0.3B
•
Updated
Oct 23, 2025
•
3
OptimizerStudy/kron_130m_4
0.3B
•
Updated
Oct 23, 2025
•
6
OptimizerStudy/kron_130m_8
0.3B
•
Updated
Oct 23, 2025
•
13
OptimizerStudy/kron_300m_1
0.5B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/kron_300m_2
0.5B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/kron_300m_4
0.5B
•
Updated
Oct 23, 2025
•
3
OptimizerStudy/kron_300m_8
0.5B
•
Updated
Oct 23, 2025
•
25
OptimizerStudy/kron_520m_1
0.8B
•
Updated
Oct 23, 2025
•
8
OptimizerStudy/kron_520m_2
0.8B
•
Updated
Oct 23, 2025
•
6
OptimizerStudy/kron_520m_4
0.8B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/kron_520m_8
0.8B
•
Updated
Oct 23, 2025
•
37
OptimizerStudy/lion_130m_1
0.3B
•
Updated
Oct 23, 2025
•
12
OptimizerStudy/lion_130m_2
0.3B
•
Updated
Oct 23, 2025
•
3
OptimizerStudy/lion_130m_4
0.3B
•
Updated
Oct 23, 2025
•
6
OptimizerStudy/lion_130m_8
0.3B
•
Updated
Oct 23, 2025
•
14
OptimizerStudy/lion_300m_1
0.5B
•
Updated
Oct 23, 2025
•
6
OptimizerStudy/lion_300m_2
0.5B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/lion_300m_4
0.5B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/lion_300m_8
0.5B
•
Updated
Oct 23, 2025
•
27
OptimizerStudy/lion_520m_1
0.8B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/lion_520m_2
0.8B
•
Updated
Oct 23, 2025
•
11
OptimizerStudy/lion_520m_4
0.8B
•
Updated
Oct 23, 2025
•
3
OptimizerStudy/lion_520m_8
0.8B
•
Updated
Oct 23, 2025
•
28
OptimizerStudy/mars_130m_1
0.3B
•
Updated
Oct 23, 2025
•
11
OptimizerStudy/mars_130m_2
0.3B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/mars_130m_4
0.3B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/mars_130m_8
0.3B
•
Updated
Oct 23, 2025
•
14
OptimizerStudy/mars_300m_1
0.5B
•
Updated
Oct 23, 2025
•
6
OptimizerStudy/mars_300m_2
0.5B
•
Updated
Oct 23, 2025
•
3
OptimizerStudy/mars_300m_4
0.5B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/mars_300m_8
0.5B
•
Updated
Oct 23, 2025
•
25
OptimizerStudy/mars_520m_1
0.8B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/mars_520m_2
0.8B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/mars_520m_4
0.8B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/mars_520m_8
0.8B
•
Updated
Oct 23, 2025
•
27
OptimizerStudy/mini_130m_1
0.3B
•
Updated
Oct 23, 2025
•
12
OptimizerStudy/mini_130m_2
0.3B
•
Updated
Oct 23, 2025
•
8
OptimizerStudy/mini_130m_4
0.3B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/mini_130m_8
0.3B
•
Updated
Oct 23, 2025
•
13
OptimizerStudy/mini_300m_1
0.5B
•
Updated
Oct 23, 2025
•
8
OptimizerStudy/mini_300m_2
0.5B
•
Updated
Oct 23, 2025
•
3
OptimizerStudy/mini_300m_4
0.5B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/mini_300m_8
0.5B
•
Updated
Oct 23, 2025
•
14
OptimizerStudy/mini_520m_1
0.8B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/mini_520m_2
0.8B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/mini_520m_4
0.8B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/mini_520m_8
0.8B
•
Updated
Oct 23, 2025
•
26
OptimizerStudy/muon_1.2b_1
2B
•
Updated
Oct 23, 2025
•
15
OptimizerStudy/muon_1.2b_2
2B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/muon_1.2b_4
2B
•
Updated
Oct 23, 2025
•
8
OptimizerStudy/muon_1.2b_8
2B
•
Updated
Oct 23, 2025
•
100
OptimizerStudy/muon_130m_1
0.3B
•
Updated
Oct 23, 2025
•
28
OptimizerStudy/muon_130m_16
0.3B
•
Updated
Oct 23, 2025
•
5
OptimizerStudy/muon_130m_2
0.3B
•
Updated
Oct 23, 2025
•
6
OptimizerStudy/muon_130m_4
0.3B
•
Updated
Oct 23, 2025
•
22
OptimizerStudy/muon_130m_8
0.3B
•
Updated
Oct 23, 2025
•
66
OptimizerStudy/muon_300m_1
0.5B
•
Updated
Oct 23, 2025
•
59
OptimizerStudy/muon_300m_2
0.5B
•
Updated
Oct 23, 2025
•
40
OptimizerStudy/muon_300m_4
0.5B
•
Updated
Oct 23, 2025
•
49
OptimizerStudy/muon_300m_8
0.5B
•
Updated
Oct 23, 2025
•
1.09k
OptimizerStudy/muon_520m_1
0.8B
•
Updated
Oct 23, 2025
•
7
OptimizerStudy/muon_520m_2
0.8B
•
Updated
Oct 23, 2025
•
4
OptimizerStudy/muon_520m_4
0.8B
•
Updated
Oct 24, 2025
•
5
OptimizerStudy/muon_520m_8
0.8B
•
Updated
Oct 24, 2025
•
339
OptimizerStudy/nadamw_1.2b_1
2B
•
Updated
Oct 24, 2025
•
9
OptimizerStudy/nadamw_1.2b_2
2B
•
Updated
Oct 24, 2025
•
3
OptimizerStudy/nadamw_1.2b_4
2B
•
Updated
Oct 24, 2025
•
7
OptimizerStudy/nadamw_1.2b_8
2B
•
Updated
Oct 24, 2025
•
10
OptimizerStudy/nadamw_130m_1
0.3B
•
Updated
Oct 24, 2025
•
13
OptimizerStudy/nadamw_130m_16
0.3B
•
Updated
Oct 24, 2025
•
7
OptimizerStudy/nadamw_130m_2
0.3B
•
Updated
Oct 24, 2025
•
4
OptimizerStudy/nadamw_130m_4
0.3B
•
Updated
Oct 24, 2025
•
3
OptimizerStudy/nadamw_130m_8
0.3B
•
Updated
Oct 24, 2025
•
13
OptimizerStudy/nadamw_300m_1
0.5B
•
Updated
Oct 24, 2025
•
7
OptimizerStudy/nadamw_300m_16
0.5B
•
Updated
Oct 24, 2025
•
7
OptimizerStudy/nadamw_300m_2
0.5B
•
Updated
Oct 24, 2025
•
5
OptimizerStudy/nadamw_300m_4
0.5B
•
Updated
Oct 24, 2025
•
9
OptimizerStudy/nadamw_300m_8
0.5B
•
Updated
Oct 24, 2025
•
28
OptimizerStudy/nadamw_520m_1
0.8B
•
Updated
Oct 24, 2025
•
7
OptimizerStudy/nadamw_520m_2
0.8B
•
Updated
Oct 24, 2025
•
4
OptimizerStudy/nadamw_520m_4
0.8B
•
Updated
Oct 24, 2025
•
6
OptimizerStudy/nadamw_520m_8
0.8B
•
Updated
Oct 24, 2025
•
33
OptimizerStudy/scion_130m_1
0.3B
•
Updated
Oct 24, 2025
•
13
OptimizerStudy/scion_130m_2
0.3B
•
Updated
Oct 24, 2025
•
6
OptimizerStudy/scion_130m_4
0.3B
•
Updated
Oct 24, 2025
•
4
OptimizerStudy/scion_130m_8
0.3B
•
Updated
Oct 24, 2025
•
12
OptimizerStudy/scion_300m_1
0.5B
•
Updated
Oct 24, 2025
•
7
OptimizerStudy/scion_300m_2
0.5B
•
Updated
Oct 24, 2025
•
5
OptimizerStudy/scion_300m_4
0.5B
•
Updated
Oct 24, 2025
•
4
OptimizerStudy/scion_300m_8
0.5B
•
Updated
Oct 24, 2025
•
25
OptimizerStudy/scion_520m_1
0.8B
•
Updated
Oct 24, 2025
•
6
OptimizerStudy/scion_520m_2
0.8B
•
Updated
Oct 24, 2025
•
4
OptimizerStudy/scion_520m_4
0.8B
•
Updated
Oct 24, 2025
•
3
OptimizerStudy/scion_520m_8
0.8B
•
Updated
Oct 24, 2025
•
30
OptimizerStudy/soape_1.2b_1
2B
•
Updated
Oct 24, 2025
•
14
OptimizerStudy/soape_1.2b_2
2B
•
Updated
Oct 24, 2025
•
7
OptimizerStudy/soape_1.2b_4
2B
•
Updated
Oct 24, 2025
•
9
OptimizerStudy/soape_1.2b_8
2B
•
Updated
Oct 24, 2025
•
14
OptimizerStudy/soape_130m_1
0.3B
•
Updated
Oct 24, 2025
•
13
OptimizerStudy/soape_130m_16
0.3B
•
Updated
Oct 24, 2025
•
8
OptimizerStudy/soape_130m_2
0.3B
•
Updated
Oct 24, 2025
•
9
OptimizerStudy/soape_130m_4
0.3B
•
Updated
Oct 24, 2025
•
10
OptimizerStudy/soape_130m_8
0.3B
•
Updated
Oct 24, 2025
•
12
OptimizerStudy/soape_300m_1
0.5B
•
Updated
Oct 24, 2025
•
10
OptimizerStudy/soape_300m_16
0.5B
•
Updated
Oct 24, 2025
•
10
OptimizerStudy/soape_300m_2
0.5B
•
Updated
Oct 24, 2025
•
5
OptimizerStudy/soape_300m_4
0.5B
•
Updated
Oct 24, 2025
•
6
OptimizerStudy/soape_300m_8
0.5B
•
Updated
Oct 24, 2025
•
31
OptimizerStudy/soape_520m_1
0.8B
•
Updated
Oct 24, 2025
•
8
OptimizerStudy/soape_520m_2
0.8B
•
Updated
Oct 24, 2025
•
5
OptimizerStudy/soape_520m_4
0.8B
•
Updated
Oct 24, 2025
•
4
OptimizerStudy/soape_520m_8
0.8B
•
Updated
Oct 24, 2025
•
33
OptimizerStudy/sophia_130m_1
0.3B
•
Updated
Oct 24, 2025
•
15
OptimizerStudy/sophia_130m_2
0.3B
•
Updated
Oct 24, 2025
•
7
OptimizerStudy/sophia_130m_4
0.3B
•
Updated
Oct 24, 2025
•
5
OptimizerStudy/sophia_130m_8
0.3B
•
Updated
Oct 24, 2025
•
15
OptimizerStudy/sophia_300m_1
0.5B
•
Updated
Oct 24, 2025
•
15
OptimizerStudy/sophia_520m_1
0.8B
•
Updated
Oct 24, 2025
•
9
Upvote
-
Sort: Collection
Share collection
View history
Collection guide
Browse collections