Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

emilianJR/epiCRealism

Text-to-Image • 0.9B • Updated Jul 23, 2023 • 11.5k • 86

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

Paper • 2609.04083 • Published Sep 3 • 24
Alibaba-NLP/core-reranker-8b

Feature Extraction • 9B • Updated Sep 4 • 93 • 1
Alibaba-NLP/core-reranker-2b

Feature Extraction • 2B • Updated Sep 4 • 133 • 2
Alibaba-NLP/core-emb-2b

Feature Extraction • Updated Sep 4 • 104 • 3

small-models-for-glam/kraken-ppocrv6-medium

Image-to-Text • Updated 2 days ago • 18

TerraDiT / TerraDiT-Omega: diffusion transformers for satellite image synthesis with text, geolocation, points, and geospatial primitives (ECCV 2026).

MVRL/TerraDiT

Text-to-Image • Updated Sep 4 • 2
MVRL/TerraDiT-data

Viewer • Updated Sep 4 • 4.39M • 79 • 1
TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive

Paper • 2606.31029 • Published Jun 30 • 5
TerraDiT: Point-Conditioned Diffusion Transformer for Satellite Image Synthesis

Paper • 2603.02172 • Published Jun 26 • 1

Best medium-sized models (8 to 30B)

inclusionAI/Ling-3.0-tiny

Text Generation • 8B • Updated Sep 24 • 12.3k • 552
google/gemma-4-12B-it

Any-to-Any • 12B • Updated Jul 20 • 1.72M • 1.69k
Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 7.76M • • 18.4k

Diffusion LAIR Models

Model checkpoints for SD1.5 and SDXL post-trained with the LAIR objective (https://arxiv.org/pdf/2605.26491)

austin-k-wang/DiffusionLAIR-SD1.5

Text-to-Image • 0.9B • Updated Aug 31 • 14 • 1
austin-k-wang/DiffusionLAIR-SDXL

Text-to-Image • 3B • Updated Aug 31 • 1

DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Image-Text-to-Text • 9B • Updated 8 days ago • 1.87M • 1.21k
jica98/qwen3.5-4B-super-coder

Text Generation • 4B • Updated Jun 27 • 25.5k • 124

Darkstar Nemotron-3-Nano-Omni 30B-A3B

Darkstar Nemotron-3-Nano-Omni family: Ablit-BF16, Base-NVFP4 (control), Ablit-NVFP4 (final servable). All gates measured in model-forge.

HangGlidersRule/Darkstar-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Abliterated-BF16

Image-Text-to-Text • 33B • Updated Sep 2 • 80
HangGlidersRule/Darkstar-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Base-ModelOpt-W4A16-NVFP4

Image-Text-to-Text • 16B • Updated Sep 4 • 23
HangGlidersRule/Darkstar-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Abliterated-ModelOpt-W4A16-NVFP4

Image-Text-to-Text • 16B • Updated Sep 4 • 31

Running

Raddarspx

🐠

Monitor real-time SPX500 options liquidity and signals

FX-FeiHou/wan2.2-Remix

Updated Mar 24 • 570

emilianJR/epiCRealism

Text-to-Image • 0.9B • Updated Jul 23, 2023 • 11.5k • 86

Diffusion LAIR Models

Model checkpoints for SD1.5 and SDXL post-trained with the LAIR objective (https://arxiv.org/pdf/2605.26491)

austin-k-wang/DiffusionLAIR-SD1.5

Text-to-Image • 0.9B • Updated Aug 31 • 14 • 1
austin-k-wang/DiffusionLAIR-SDXL

Text-to-Image • 3B • Updated Aug 31 • 1

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

Paper • 2609.04083 • Published Sep 3 • 24
Alibaba-NLP/core-reranker-8b

Feature Extraction • 9B • Updated Sep 4 • 93 • 1
Alibaba-NLP/core-reranker-2b

Feature Extraction • 2B • Updated Sep 4 • 133 • 2
Alibaba-NLP/core-emb-2b

Feature Extraction • Updated Sep 4 • 104 • 3

DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Image-Text-to-Text • 9B • Updated 8 days ago • 1.87M • 1.21k
jica98/qwen3.5-4B-super-coder

Text Generation • 4B • Updated Jun 27 • 25.5k • 124

small-models-for-glam/kraken-ppocrv6-medium

Image-to-Text • Updated 2 days ago • 18

Darkstar Nemotron-3-Nano-Omni 30B-A3B

Darkstar Nemotron-3-Nano-Omni family: Ablit-BF16, Base-NVFP4 (control), Ablit-NVFP4 (final servable). All gates measured in model-forge.

HangGlidersRule/Darkstar-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Abliterated-BF16

Image-Text-to-Text • 33B • Updated Sep 2 • 80
HangGlidersRule/Darkstar-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Base-ModelOpt-W4A16-NVFP4

Image-Text-to-Text • 16B • Updated Sep 4 • 23
HangGlidersRule/Darkstar-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Abliterated-ModelOpt-W4A16-NVFP4

Image-Text-to-Text • 16B • Updated Sep 4 • 31

TerraDiT / TerraDiT-Omega: diffusion transformers for satellite image synthesis with text, geolocation, points, and geospatial primitives (ECCV 2026).

MVRL/TerraDiT

Text-to-Image • Updated Sep 4 • 2
MVRL/TerraDiT-data

Viewer • Updated Sep 4 • 4.39M • 79 • 1
TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive

Paper • 2606.31029 • Published Jun 30 • 5
TerraDiT: Point-Conditioned Diffusion Transformer for Satellite Image Synthesis

Paper • 2603.02172 • Published Jun 26 • 1

Running

Raddarspx

🐠

Monitor real-time SPX500 options liquidity and signals

Best medium-sized models (8 to 30B)

inclusionAI/Ling-3.0-tiny

Text Generation • 8B • Updated Sep 24 • 12.3k • 552
google/gemma-4-12B-it

Any-to-Any • 12B • Updated Jul 20 • 1.72M • 1.69k
Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 7.76M • • 18.4k

FX-FeiHou/wan2.2-Remix

Updated Mar 24 • 570

Previous
1
...
1,443
1,444
1,445
1,446
1,447
...
24,305
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs