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

Our most capable model to date, designed for long-horizon work. Apache 2.0.

poolside/Laguna-M.1

Text Generation • 226B • Updated about 19 hours ago • 3.31k • 101
poolside/Laguna-M.1-base

Text Generation • 226B • Updated 14 days ago • 675 • 13
poolside/Laguna-M.1-NVFP4

Text Generation • 131B • Updated about 19 hours ago • 3.13k • 10
poolside/Laguna-M.1-FP8

Text Generation • 226B • Updated about 19 hours ago • 1.8k • 10

Qwen3.5-Claude-Fable-5

Our series of Qwen3.5 finetunes on Claude-Fable-5 outputs

empero-ai/Qwable-9B-Claude-Fable-5

Text Generation • 9B • Updated 13 days ago • 26.9k • 74
empero-ai/Qwable-9B-Claude-Fable-5-GGUF

Image-Text-to-Text • 9B • Updated 13 days ago • 30.7k • 49

Gemma 4 QAT Mobile

google/gemma-4-E2B-it-qat-mobile-transformers

Any-to-Any • 2B • Updated 26 days ago • 21.1k • 95
google/gemma-4-E4B-it-qat-mobile-transformers

Any-to-Any • 3B • Updated 26 days ago • 2.96k • 21
google/gemma-4-E2B-it-qat-mobile-ct

Any-to-Any • 6B • Updated 26 days ago • 5.64k • 20
google/gemma-4-E4B-it-qat-mobile-ct

Any-to-Any • 9B • Updated 26 days ago • 10.1k • 18

Natural Language Autoencoders across Llama, Gemma, and Qwen. Code: https://github.com/kitft/natural_language_autoencoders/

kitft/Llama-3.3-70B-NLA-L53-ar

47B • Updated May 7 • 33
kitft/Llama-3.3-70B-NLA-L53-av

71B • Updated May 7 • 72
kitft/nla-gemma3-27b-L41-ar

19B • Updated May 7 • 63 • 4
kitft/nla-gemma3-27b-L41-av

27B • Updated May 7 • 696 • 5

Qwen3.6-abliterated

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

Image-Text-to-Text • 36B • Updated Apr 18 • 12.7k • 67
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

Image-Text-to-Text • 36B • Updated Apr 21 • 519 • 23
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

Text Generation • 36B • Updated Apr 21 • 38.3k • 156
huihui-ai/Huihui-Qwen3.6-27B-abliterated

Image-Text-to-Text • 28B • Updated Apr 23 • 12.5k • 58

French medical encoders pretrained from scratch on curated and LLM-rephrased medical web data.

doctolib-lab/doctomodernbert-fr-base

Fill-Mask • 0.1B • Updated 9 days ago • 54
doctolib-lab/doctobert-fr-base

Fill-Mask • 0.1B • Updated 9 days ago • 134 • 5
doctolib-lab/doctobert-fr-ckpts

Updated 9 days ago • 1
Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining

Paper • 2606.22079 • Published 12 days ago • 2

Gemma 4 MTP QAT

mlx-community/gemma-4-12B-it-qat-assistant-4bit

Text Generation • 66.1M • Updated 26 days ago • 4.58k • 2
mlx-community/gemma-4-12B-it-qat-assistant-5bit

Text Generation • 79.3M • Updated 26 days ago • 417
mlx-community/gemma-4-12B-it-qat-assistant-6bit

Text Generation • 92.5M • Updated 26 days ago • 459
mlx-community/gemma-4-12B-it-qat-assistant-8bit

Text Generation • 0.1B • Updated 26 days ago • 1.03k

Mellum2 GGUF weights

JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-BF16

Text Generation • 12B • Updated 28 days ago • 958 • 6
JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q8_0

Text Generation • 12B • Updated 28 days ago • 4.4k • 18
JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q6_K

Text Generation • 12B • Updated 28 days ago • 2.25k • 11
JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M

Text Generation • 12B • Updated 28 days ago • 19.4k • 31

Qwen 3.6 — AEON Ultimate Uncensored & Heretic

Lossless abliteration of Qwen3.6-27B with full multimodal preservation. NVFP4 + MTP/MTP-XS variants. DGX Spark production-validated.

about 3 hours ago

AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16

Text Generation • 27B • Updated 4 days ago • 18k • • 123
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS

Text Generation • 17B • Updated 4 days ago • 34.4k • 51
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP

Text Generation • 20B • Updated 4 days ago • 37k • 21
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4

Text Generation • 19B • Updated 4 days ago • 21.1k • 81

swe-zero-to-swe-hero

Datasets and Models for SWE-ZERO to SWE-HERO paper (https://arxiv.org/abs/2604.01496)

nvidia/SWE-Zero-openhands-trajectories

Viewer • Updated May 5 • 318k • 2.27k • 14
nvidia/SWE-Hero-openhands-trajectories

Viewer • Updated May 8 • 34.3k • 2.39k • 17
From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

Paper • 2604.01496 • Published Apr 2 • 2

Our most capable model to date, designed for long-horizon work. Apache 2.0.

poolside/Laguna-M.1

Text Generation • 226B • Updated about 19 hours ago • 3.31k • 101
poolside/Laguna-M.1-base

Text Generation • 226B • Updated 14 days ago • 675 • 13
poolside/Laguna-M.1-NVFP4

Text Generation • 131B • Updated about 19 hours ago • 3.13k • 10
poolside/Laguna-M.1-FP8

Text Generation • 226B • Updated about 19 hours ago • 1.8k • 10

French medical encoders pretrained from scratch on curated and LLM-rephrased medical web data.

doctolib-lab/doctomodernbert-fr-base

Fill-Mask • 0.1B • Updated 9 days ago • 54
doctolib-lab/doctobert-fr-base

Fill-Mask • 0.1B • Updated 9 days ago • 134 • 5
doctolib-lab/doctobert-fr-ckpts

Updated 9 days ago • 1
Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining

Paper • 2606.22079 • Published 12 days ago • 2

Qwen3.5-Claude-Fable-5

Our series of Qwen3.5 finetunes on Claude-Fable-5 outputs

empero-ai/Qwable-9B-Claude-Fable-5

Text Generation • 9B • Updated 13 days ago • 26.9k • 74
empero-ai/Qwable-9B-Claude-Fable-5-GGUF

Image-Text-to-Text • 9B • Updated 13 days ago • 30.7k • 49

Gemma 4 MTP QAT

mlx-community/gemma-4-12B-it-qat-assistant-4bit

Text Generation • 66.1M • Updated 26 days ago • 4.58k • 2
mlx-community/gemma-4-12B-it-qat-assistant-5bit

Text Generation • 79.3M • Updated 26 days ago • 417
mlx-community/gemma-4-12B-it-qat-assistant-6bit

Text Generation • 92.5M • Updated 26 days ago • 459
mlx-community/gemma-4-12B-it-qat-assistant-8bit

Text Generation • 0.1B • Updated 26 days ago • 1.03k

Gemma 4 QAT Mobile

google/gemma-4-E2B-it-qat-mobile-transformers

Any-to-Any • 2B • Updated 26 days ago • 21.1k • 95
google/gemma-4-E4B-it-qat-mobile-transformers

Any-to-Any • 3B • Updated 26 days ago • 2.96k • 21
google/gemma-4-E2B-it-qat-mobile-ct

Any-to-Any • 6B • Updated 26 days ago • 5.64k • 20
google/gemma-4-E4B-it-qat-mobile-ct

Any-to-Any • 9B • Updated 26 days ago • 10.1k • 18

Mellum2 GGUF weights

JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-BF16

Text Generation • 12B • Updated 28 days ago • 958 • 6
JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q8_0

Text Generation • 12B • Updated 28 days ago • 4.4k • 18
JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q6_K

Text Generation • 12B • Updated 28 days ago • 2.25k • 11
JetBrains/Mellum2-12B-A2.5B-Thinking-GGUF-Q4_K_M

Text Generation • 12B • Updated 28 days ago • 19.4k • 31

Natural Language Autoencoders across Llama, Gemma, and Qwen. Code: https://github.com/kitft/natural_language_autoencoders/

kitft/Llama-3.3-70B-NLA-L53-ar

47B • Updated May 7 • 33
kitft/Llama-3.3-70B-NLA-L53-av

71B • Updated May 7 • 72
kitft/nla-gemma3-27b-L41-ar

19B • Updated May 7 • 63 • 4
kitft/nla-gemma3-27b-L41-av

27B • Updated May 7 • 696 • 5

Qwen 3.6 — AEON Ultimate Uncensored & Heretic

Lossless abliteration of Qwen3.6-27B with full multimodal preservation. NVFP4 + MTP/MTP-XS variants. DGX Spark production-validated.

about 3 hours ago

AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16

Text Generation • 27B • Updated 4 days ago • 18k • • 123
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP-XS

Text Generation • 17B • Updated 4 days ago • 34.4k • 51
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-Multimodal-NVFP4-MTP

Text Generation • 20B • Updated 4 days ago • 37k • 21
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-NVFP4

Text Generation • 19B • Updated 4 days ago • 21.1k • 81

Qwen3.6-abliterated

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

Image-Text-to-Text • 36B • Updated Apr 18 • 12.7k • 67
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

Image-Text-to-Text • 36B • Updated Apr 21 • 519 • 23
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

Text Generation • 36B • Updated Apr 21 • 38.3k • 156
huihui-ai/Huihui-Qwen3.6-27B-abliterated

Image-Text-to-Text • 28B • Updated Apr 23 • 12.5k • 58

swe-zero-to-swe-hero

Datasets and Models for SWE-ZERO to SWE-HERO paper (https://arxiv.org/abs/2604.01496)

nvidia/SWE-Zero-openhands-trajectories

Viewer • Updated May 5 • 318k • 2.27k • 14
nvidia/SWE-Hero-openhands-trajectories

Viewer • Updated May 8 • 34.3k • 2.39k • 17
From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents

Paper • 2604.01496 • Published Apr 2 • 2

Previous
1
...
8
9
10
11
12
...
21,503
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs