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

facebook/SACo-Gold

Viewer • Updated Nov 17, 2025 • 21 • 222 • 24
facebook/SACo-Silver

Viewer • Updated Nov 17, 2025 • 9 • 63 • 7
facebook/SACo-VEval

Viewer • Updated Nov 17, 2025 • 2 • 91 • 4
facebook/SA-FARI

Updated Nov 19, 2025 • 56 • 24

Qwen/Qwen3-235B-A22B-Thinking-2507-FP8

Text Generation • 235B • Updated Jul 30, 2025 • 49.6k • 87
Qwen/Qwen3-235B-A22B-Thinking-2507

Text Generation • 235B • Updated Aug 17, 2025 • 29.9k • • 408
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8

Text Generation • 235B • Updated Sep 17, 2025 • 59k • 147
Qwen/Qwen3-235B-A22B-Instruct-2507

Text Generation • 235B • Updated Sep 17, 2025 • 46.6k • • 793

Open Source AI Summer

13 open-weight drops across text, video, voice and safety

deepseek-ai/DeepSeek-V4-Flash-0731

Text Generation • 304B • Updated 14 days ago • 1.8M • • 3.41k
meta-models/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated 4 days ago • 246k • • 1.55k
LiquidAI/LFM2.5-2.6B

Text Generation • 3B • Updated 8 days ago • 135k • 624
inclusionAI/Ling-3.0-flash

Text Generation • 127B • Updated 9 days ago • 12.2k • 336

Recursive Synthesis for Long-Horizon Terminal Tasks

CC BY 4.0 datasets and SFT/RL checkpoints for recursive task synthesis; base-model and third-party terms still apply.

Zhongzhi1228/Recursive-Task-Synthesis

Viewer • Updated 9 days ago • 37.5k • 955 • 16
Zhongzhi1228/Recursive-Task-Synthesis-Trajectories

Viewer • Updated 9 days ago • 327k • 1.04k • 3
Zhongzhi1228/Qwen3.5-27B-SFT

Image-Text-to-Text • 28B • Updated 10 days ago • 55 • 1
Zhongzhi1228/Qwen3.5-122B-A10B-SFT

Image-Text-to-Text • 125B • Updated 8 days ago • 66 • 1

Qwen3.6-abliterated

huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated

Image-Text-to-Text • 36B • Updated Apr 18 • 25.8k • • 85
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

Image-Text-to-Text • 36B • Updated Apr 21 • 647 • 23
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

Text Generation • 36B • Updated Apr 21 • 24.7k • • 208
huihui-ai/Huihui-Qwen3.6-27B-abliterated

Image-Text-to-Text • 28B • Updated Apr 23 • 18.5k • • 71

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104

facebook/dinov3-vit7b16-pretrain-lvd1689m

Image Feature Extraction • 7B • Updated Aug 19, 2025 • 16.3k • 244
facebook/dinov3-vits16-pretrain-lvd1689m

Image Feature Extraction • 21.6M • Updated Aug 19, 2025 • 406k • 158
facebook/dinov3-convnext-small-pretrain-lvd1689m

Image Feature Extraction • 49.5M • Updated Aug 19, 2025 • 26.8k • 34
facebook/dinov3-vitb16-pretrain-lvd1689m

Image Feature Extraction • 85.7M • Updated Aug 19, 2025 • 644k • 214

North-Micro-Vision

MLX quantizations of CohereLabs/North-Micro-Vision-Instruct.

mlx-community/North-Micro-Vision-Instruct-4bit

Image-Text-to-Text • 0.8B • Updated 3 days ago • 120
mlx-community/North-Micro-Vision-Instruct-5bit

Image-Text-to-Text • 0.9B • Updated 3 days ago • 34
mlx-community/North-Micro-Vision-Instruct-6bit

Image-Text-to-Text • 1.0B • Updated 3 days ago • 43
mlx-community/North-Micro-Vision-Instruct-8bit

Image-Text-to-Text • 1B • Updated 3 days ago • 78

Quants for Meta's new Muse Glimmer 30B model.

unsloth/Muse-Glimmer-30B-GGUF

Image-Text-to-Text • 28B • Updated 5 days ago • 682k • 428
unsloth/Muse-Glimmer-30B-unsloth-bnb-4bit

Image-Text-to-Text • 30B • Updated 5 days ago • 5.9k • 10
unsloth/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated 5 days ago • 85.6k • 12

Borealis is a new family of Norwegian-centric instruction-tuned language models from the National Library of Norway.

NbAiLab/borealis-27b

Image-Text-to-Text • 27B • Updated May 25 • 1.15k • 8
NbAiLab/borealis-12b

Image-Text-to-Text • 12B • Updated May 25 • 397
NbAiLab/borealis-4b

Image-Text-to-Text • 4B • Updated May 25 • 193 • 1
NbAiLab/borealis-1b

Text Generation • 1.0B • Updated May 25 • 135

Pre-1900 LLMs for physics reasoning. RL models are physics-only; use the SFT model for general chat. Tune temperature (0.6-0.7).

mhla/gpt1900-d34-22btok

Updated Mar 29 • 7
mhla/gpt1905-d34

Updated Mar 29 • 4
mhla/gpt1964-d34

Updated Mar 31
mhla/gpt1900-instruct-v3-sft

Updated Apr 2 • 5

facebook/SACo-Gold

Viewer • Updated Nov 17, 2025 • 21 • 222 • 24
facebook/SACo-Silver

Viewer • Updated Nov 17, 2025 • 9 • 63 • 7
facebook/SACo-VEval

Viewer • Updated Nov 17, 2025 • 2 • 91 • 4
facebook/SA-FARI

Updated Nov 19, 2025 • 56 • 24

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104

facebook/dinov3-vit7b16-pretrain-lvd1689m

Image Feature Extraction • 7B • Updated Aug 19, 2025 • 16.3k • 244
facebook/dinov3-vits16-pretrain-lvd1689m

Image Feature Extraction • 21.6M • Updated Aug 19, 2025 • 406k • 158
facebook/dinov3-convnext-small-pretrain-lvd1689m

Image Feature Extraction • 49.5M • Updated Aug 19, 2025 • 26.8k • 34
facebook/dinov3-vitb16-pretrain-lvd1689m

Image Feature Extraction • 85.7M • Updated Aug 19, 2025 • 644k • 214

Qwen/Qwen3-235B-A22B-Thinking-2507-FP8

Text Generation • 235B • Updated Jul 30, 2025 • 49.6k • 87
Qwen/Qwen3-235B-A22B-Thinking-2507

Text Generation • 235B • Updated Aug 17, 2025 • 29.9k • • 408
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8

Text Generation • 235B • Updated Sep 17, 2025 • 59k • 147
Qwen/Qwen3-235B-A22B-Instruct-2507

Text Generation • 235B • Updated Sep 17, 2025 • 46.6k • • 793

North-Micro-Vision

MLX quantizations of CohereLabs/North-Micro-Vision-Instruct.

mlx-community/North-Micro-Vision-Instruct-4bit

Image-Text-to-Text • 0.8B • Updated 3 days ago • 120
mlx-community/North-Micro-Vision-Instruct-5bit

Image-Text-to-Text • 0.9B • Updated 3 days ago • 34
mlx-community/North-Micro-Vision-Instruct-6bit

Image-Text-to-Text • 1.0B • Updated 3 days ago • 43
mlx-community/North-Micro-Vision-Instruct-8bit

Image-Text-to-Text • 1B • Updated 3 days ago • 78

Open Source AI Summer

13 open-weight drops across text, video, voice and safety

deepseek-ai/DeepSeek-V4-Flash-0731

Text Generation • 304B • Updated 14 days ago • 1.8M • • 3.41k
meta-models/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated 4 days ago • 246k • • 1.55k
LiquidAI/LFM2.5-2.6B

Text Generation • 3B • Updated 8 days ago • 135k • 624
inclusionAI/Ling-3.0-flash

Text Generation • 127B • Updated 9 days ago • 12.2k • 336

Quants for Meta's new Muse Glimmer 30B model.

unsloth/Muse-Glimmer-30B-GGUF

Image-Text-to-Text • 28B • Updated 5 days ago • 682k • 428
unsloth/Muse-Glimmer-30B-unsloth-bnb-4bit

Image-Text-to-Text • 30B • Updated 5 days ago • 5.9k • 10
unsloth/Muse-Glimmer-30B

Image-Text-to-Text • 30B • Updated 5 days ago • 85.6k • 12

Recursive Synthesis for Long-Horizon Terminal Tasks

CC BY 4.0 datasets and SFT/RL checkpoints for recursive task synthesis; base-model and third-party terms still apply.

Zhongzhi1228/Recursive-Task-Synthesis

Viewer • Updated 9 days ago • 37.5k • 955 • 16
Zhongzhi1228/Recursive-Task-Synthesis-Trajectories

Viewer • Updated 9 days ago • 327k • 1.04k • 3
Zhongzhi1228/Qwen3.5-27B-SFT

Image-Text-to-Text • 28B • Updated 10 days ago • 55 • 1
Zhongzhi1228/Qwen3.5-122B-A10B-SFT

Image-Text-to-Text • 125B • Updated 8 days ago • 66 • 1

Borealis is a new family of Norwegian-centric instruction-tuned language models from the National Library of Norway.

NbAiLab/borealis-27b

Image-Text-to-Text • 27B • Updated May 25 • 1.15k • 8
NbAiLab/borealis-12b

Image-Text-to-Text • 12B • Updated May 25 • 397
NbAiLab/borealis-4b

Image-Text-to-Text • 4B • Updated May 25 • 193 • 1
NbAiLab/borealis-1b

Text Generation • 1.0B • Updated May 25 • 135

Qwen3.6-abliterated

huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated

Image-Text-to-Text • 36B • Updated Apr 18 • 25.8k • • 85
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

Image-Text-to-Text • 36B • Updated Apr 21 • 647 • 23
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

Text Generation • 36B • Updated Apr 21 • 24.7k • • 208
huihui-ai/Huihui-Qwen3.6-27B-abliterated

Image-Text-to-Text • 28B • Updated Apr 23 • 18.5k • • 71

Pre-1900 LLMs for physics reasoning. RL models are physics-only; use the SFT model for general chat. Tune temperature (0.6-0.7).

mhla/gpt1900-d34-22btok

Updated Mar 29 • 7
mhla/gpt1905-d34

Updated Mar 29 • 4
mhla/gpt1964-d34

Updated Mar 31
mhla/gpt1900-instruct-v3-sft

Updated Apr 2 • 5

Previous
1
2
3
4
5
6
...
22,496
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs