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

Running

180

Bonsai 27B WebGPU Kernels

🌳

180

Run a 1-bit 27B LLM locally in your browser on WebGPU
Running on CPU Upgrade

Agents

10

Ternary Bonsai 27B API Demo

🤗

10

Chat with the Ternary Bonsai 27B language model
prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 4B • Updated about 3 hours ago • 201k • • 664
prism-ml/Bonsai-27B-gguf

Text Generation • 4B • Updated about 3 hours ago • 1.05M • 380

Dynamic Unsloth NVFP4 Quants. Faster and more accurate.

unsloth/gemma-4-31B-it-NVFP4

Image-Text-to-Text • 23B • Updated 2 days ago • 5.91k • 20
unsloth/gemma-4-26B-A4B-it-NVFP4

Image-Text-to-Text • 16B • Updated 2 days ago • 9.85k • 13
unsloth/gemma-4-12b-it-NVFP4

Image-Text-to-Text • 8B • Updated 2 days ago • 7.53k • 13
unsloth/gemma-4-E4B-it-NVFP4

Image-Text-to-Text • 7B • Updated 2 days ago • 1.69k • 7

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding.

Running on Zero

Agents

Featured

68

Ornith 1.0 9B

📊

68

Chat with an AI coding assistant that explains its reasoning
deepreinforce-ai/Ornith-1.0-9B

Text Generation • 1.47M • Updated 22 days ago • 887k • • 461
deepreinforce-ai/Ornith-1.0-35B

Text Generation • 665k • Updated 22 days ago • 1.28M • • 403
deepreinforce-ai/Ornith-1.0-397B

Text Generation • 397B • Updated 22 days ago • 252k • 235

T-Search model and evaluation datasets.

about 22 hours ago

t-tech/T-Search

Text Generation • 36B • Updated 1 day ago • 18 • 17
t-tech/TRuST

Viewer • Updated 1 day ago • 324 • 7 • 11
t-tech/SynthComp

Viewer • Updated 1 day ago • 790 • 10 • 9
t-tech/T-Search-FP8

Text Generation • 36B • Updated 1 day ago • 21 • 10

about 10 hours ago

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published 2 days ago • 107
MCG-NJU/I3D-ViT

Image Feature Extraction • 0.4B • Updated about 15 hours ago • 10 • 5
MCG-NJU/VideoChat3-4B

Video-Text-to-Text • 4B • Updated about 7 hours ago • 20 • 8
MCG-NJU/VideoChat3-LV116k

Viewer • Updated 9 minutes ago • 8.07k • 5.07k • 6

Soofi S Beta Models

about 7 hours ago

Soofi-Project/Soofi-S-Base

Text Generation • 32B • Updated about 6 hours ago • 95 • 41
Soofi-Project/Soofi-S-Rhine-Preview

Text Generation • 32B • Updated about 7 hours ago • 620 • 13
Soofi-Project/Soofi-S-Instruct-Preview

Text Generation • 32B • Updated about 7 hours ago • 3.38k • 16
Soofi-Project/Soofi-S-Isar-Preview

Text Generation • 32B • Updated about 7 hours ago • 3.16k • 12

Inkling is a versatile, customizable model that reasons over text, images, audio, with variable and efficient thinking effort.

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated 1 day ago • 7.87k • • 935
thinkingmachines/Inkling-NVFP4

Image-Text-to-Text • 553B • Updated 1 day ago • 38.4k • 60

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated 2 days ago • 12.5M • • 3.25k
google/gemma-4-31B

Image-Text-to-Text • 33B • Updated 2 days ago • 816k • 470
google/gemma-4-26B-A4B-it

Image-Text-to-Text • 27B • Updated 2 days ago • 14.1M • • 1.28k
google/gemma-4-26B-A4B

Image-Text-to-Text • 27B • Updated 2 days ago • 1.06M • 344

Nemotron 3 Embed

Open embedding models for enterprise RAG, agentic retrieval, code search, and agent memory.

about 21 hours ago

nvidia/Nemotron-3-Embed-1B-NVFP4

Sentence Similarity • 0.8B • Updated about 6 hours ago • 5.74k • 41
nvidia/Nemotron-3-Embed-1B-BF16

Sentence Similarity • 1B • Updated 1 day ago • 46.3k • 58
nvidia/Nemotron-3-Embed-8B-BF16

Sentence Similarity • 8B • Updated 2 days ago • 13k • 47

deepseek-ai/DeepSeek-V4-Flash-Base

292B • Updated Apr 27 • 89k • 272
deepseek-ai/DeepSeek-V4-Flash

Text Generation • 158B • Updated 25 days ago • 2.94M • • 1.76k
deepseek-ai/DeepSeek-V4-Pro-Base

1.6T • Updated Apr 27 • 42.7k • 311
deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 25 days ago • 1.48M • • 5.24k

Running

180

Bonsai 27B WebGPU Kernels

🌳

180

Run a 1-bit 27B LLM locally in your browser on WebGPU
Running on CPU Upgrade

Agents

10

Ternary Bonsai 27B API Demo

🤗

10

Chat with the Ternary Bonsai 27B language model
prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 4B • Updated about 3 hours ago • 201k • • 664
prism-ml/Bonsai-27B-gguf

Text Generation • 4B • Updated about 3 hours ago • 1.05M • 380

Soofi S Beta Models

about 7 hours ago

Soofi-Project/Soofi-S-Base

Text Generation • 32B • Updated about 6 hours ago • 95 • 41
Soofi-Project/Soofi-S-Rhine-Preview

Text Generation • 32B • Updated about 7 hours ago • 620 • 13
Soofi-Project/Soofi-S-Instruct-Preview

Text Generation • 32B • Updated about 7 hours ago • 3.38k • 16
Soofi-Project/Soofi-S-Isar-Preview

Text Generation • 32B • Updated about 7 hours ago • 3.16k • 12

Dynamic Unsloth NVFP4 Quants. Faster and more accurate.

unsloth/gemma-4-31B-it-NVFP4

Image-Text-to-Text • 23B • Updated 2 days ago • 5.91k • 20
unsloth/gemma-4-26B-A4B-it-NVFP4

Image-Text-to-Text • 16B • Updated 2 days ago • 9.85k • 13
unsloth/gemma-4-12b-it-NVFP4

Image-Text-to-Text • 8B • Updated 2 days ago • 7.53k • 13
unsloth/gemma-4-E4B-it-NVFP4

Image-Text-to-Text • 7B • Updated 2 days ago • 1.69k • 7

Inkling is a versatile, customizable model that reasons over text, images, audio, with variable and efficient thinking effort.

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated 1 day ago • 7.87k • • 935
thinkingmachines/Inkling-NVFP4

Image-Text-to-Text • 553B • Updated 1 day ago • 38.4k • 60

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding.

Running on Zero

Agents

Featured

68

Ornith 1.0 9B

📊

68

Chat with an AI coding assistant that explains its reasoning
deepreinforce-ai/Ornith-1.0-9B

Text Generation • 1.47M • Updated 22 days ago • 887k • • 461
deepreinforce-ai/Ornith-1.0-35B

Text Generation • 665k • Updated 22 days ago • 1.28M • • 403
deepreinforce-ai/Ornith-1.0-397B

Text Generation • 397B • Updated 22 days ago • 252k • 235

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated 2 days ago • 12.5M • • 3.25k
google/gemma-4-31B

Image-Text-to-Text • 33B • Updated 2 days ago • 816k • 470
google/gemma-4-26B-A4B-it

Image-Text-to-Text • 27B • Updated 2 days ago • 14.1M • • 1.28k
google/gemma-4-26B-A4B

Image-Text-to-Text • 27B • Updated 2 days ago • 1.06M • 344

T-Search model and evaluation datasets.

about 22 hours ago

t-tech/T-Search

Text Generation • 36B • Updated 1 day ago • 18 • 17
t-tech/TRuST

Viewer • Updated 1 day ago • 324 • 7 • 11
t-tech/SynthComp

Viewer • Updated 1 day ago • 790 • 10 • 9
t-tech/T-Search-FP8

Text Generation • 36B • Updated 1 day ago • 21 • 10

Nemotron 3 Embed

Open embedding models for enterprise RAG, agentic retrieval, code search, and agent memory.

about 21 hours ago

nvidia/Nemotron-3-Embed-1B-NVFP4

Sentence Similarity • 0.8B • Updated about 6 hours ago • 5.74k • 41
nvidia/Nemotron-3-Embed-1B-BF16

Sentence Similarity • 1B • Updated 1 day ago • 46.3k • 58
nvidia/Nemotron-3-Embed-8B-BF16

Sentence Similarity • 8B • Updated 2 days ago • 13k • 47

about 10 hours ago

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Paper • 2607.14935 • Published 2 days ago • 107
MCG-NJU/I3D-ViT

Image Feature Extraction • 0.4B • Updated about 15 hours ago • 10 • 5
MCG-NJU/VideoChat3-4B

Video-Text-to-Text • 4B • Updated about 7 hours ago • 20 • 8
MCG-NJU/VideoChat3-LV116k

Viewer • Updated 9 minutes ago • 8.07k • 5.07k • 6

deepseek-ai/DeepSeek-V4-Flash-Base

292B • Updated Apr 27 • 89k • 272
deepseek-ai/DeepSeek-V4-Flash

Text Generation • 158B • Updated 25 days ago • 2.94M • • 1.76k
deepseek-ai/DeepSeek-V4-Pro-Base

1.6T • Updated Apr 27 • 42.7k • 311
deepseek-ai/DeepSeek-V4-Pro

Text Generation • 862B • Updated 25 days ago • 1.48M • • 5.24k

Previous
1
2
3
...
21,852
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs