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

Collections

Discover the best community collections!

Collections trending this week

Agent / LLM evaluation

Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach

Paper • 2610.19425 • Published 24 days ago • 10

phoonnx community TTS exports

Open TTS models from the community, exported to ONNX for phoonnx: 31 engines, about 1,700 voices, MMS in 1,107 languages.

OpenVoiceOS/phoonnx-audio8-tts

Text-to-Speech • Updated Aug 3 • 20
OpenVoiceOS/phoonnx-chatterbox-lahgtna

Text-to-Speech • Updated Aug 3
OpenVoiceOS/phoonnx-chatterbox-multilingual

Text-to-Speech • Updated Aug 3
OpenVoiceOS/phoonnx-coqui-vits

Text-to-Speech • Updated Aug 3

axiomofmind/Moss-image-nsfw-uncensored-lora

Text-to-Image • Updated 13 days ago • 65k • 781

Geospatial & Location Intelligence

Models, datasets and Spaces for satellite imagery, Earth observation, mapping and location-aware applications.

ibm-esa-geospatial/TerraMind-1.0-base

Updated Nov 3, 2025 • 43.5k • 56
wikimedia/linked-openstreetmap-wikidata-wikipedia-wikivoyage

Viewer • Updated Oct 6 • 50.7M • 644 • 3
Running

Agents

13

Prithvi EO 2.0 Demo

🌎

13

Prithvi-EO-2.0-300M-TL image reconstruction demo
ibm-nasa-geospatial/Prithvi-EO-2.0-600M-TL

Updated Oct 9, 2025 • 1.36k • 17

axiomofmind/Moss-image-nsfw-uncensored-lora

Text-to-Image • Updated 13 days ago • 65k • 781

AI for Cultural Heritage & Museums

Open models and datasets for artwork recognition, archaeology, historical documents and museum collections.

sanugteknoloji/turkiye-cultural-heritage-sites

Viewer • Updated 16 days ago • 23.6k • 58 • 1
OttomanNLP/Azra-1-Mini-0.8b

Image-to-Text • 0.9B • Updated Aug 7 • 337 • 5
Running on Zero

MCP

63

HTRflow App

🏢

63

HTR (Handwritten Text Recognition) demo application
CATMuS/medieval

Viewer • Updated Mar 11, 2025 • 195k • 5.1k • 29

OpenVoiceOS voices: miro and dii

TTS voices trained by OpenVoiceOS: miro (male) and dii (female), in many languages. ONNX models for phoonnx and Piper.

OpenVoiceOS/phoonnx_an_dii_unicode

Text-to-Speech • Updated 29 days ago
OpenVoiceOS/phoonnx_an_miro_espeak

Text-to-Speech • Updated 26 days ago
OpenVoiceOS/phoonnx_an_miro_unicode

Text-to-Speech • Updated 29 days ago
OpenVoiceOS/phoonnx_ar_dii_espeak

Text-to-Speech • Updated 29 days ago

LeRobot & Hugging Face for companies

What LeRobot and the Hugging Face Hub can do for your company: from a first low-cost arm to fine-tuned robot policies.

Running on CPU Upgrade

2

LeRobot for Companies

🤖

2

How LeRobot and Hugging Face help companies start robotics
Running

Robot Setup Advisor

🦾

Right-size a robot, GPU and board; compare cost, energy, CO2
Running

1

LeRobot Presentation

🤖

1

Explore robot learning workflow through an interactive web demo

about 15 hours ago

unsloth/gemma-4-12B-it-qat-GGUF

Any-to-Any • 12B • Updated Jul 17 • 207k • 609
google/gemma-4-26B-A4B-it-qat-q4_0-gguf

Image-Text-to-Text • 25B • Updated Jul 17 • 198k • 218
unsloth/gemma-4-E4B-it-qat-mobile-GGUF

Any-to-Any • 7B • Updated Jul 17 • 48.2k • 36
byteshape/Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Sep 18 • 2.06M • 203

Decision Models

convaiinnovations/laya

Text Classification • 0.4B • Updated Oct 3 • 28.5k • • 5.92k

Agent / LLM evaluation

Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach

Paper • 2610.19425 • Published 24 days ago • 10

AI for Cultural Heritage & Museums

Open models and datasets for artwork recognition, archaeology, historical documents and museum collections.

sanugteknoloji/turkiye-cultural-heritage-sites

Viewer • Updated 16 days ago • 23.6k • 58 • 1
OttomanNLP/Azra-1-Mini-0.8b

Image-to-Text • 0.9B • Updated Aug 7 • 337 • 5
Running on Zero

MCP

63

HTRflow App

🏢

63

HTR (Handwritten Text Recognition) demo application
CATMuS/medieval

Viewer • Updated Mar 11, 2025 • 195k • 5.1k • 29

phoonnx community TTS exports

Open TTS models from the community, exported to ONNX for phoonnx: 31 engines, about 1,700 voices, MMS in 1,107 languages.

OpenVoiceOS/phoonnx-audio8-tts

Text-to-Speech • Updated Aug 3 • 20
OpenVoiceOS/phoonnx-chatterbox-lahgtna

Text-to-Speech • Updated Aug 3
OpenVoiceOS/phoonnx-chatterbox-multilingual

Text-to-Speech • Updated Aug 3
OpenVoiceOS/phoonnx-coqui-vits

Text-to-Speech • Updated Aug 3

OpenVoiceOS voices: miro and dii

TTS voices trained by OpenVoiceOS: miro (male) and dii (female), in many languages. ONNX models for phoonnx and Piper.

OpenVoiceOS/phoonnx_an_dii_unicode

Text-to-Speech • Updated 29 days ago
OpenVoiceOS/phoonnx_an_miro_espeak

Text-to-Speech • Updated 26 days ago
OpenVoiceOS/phoonnx_an_miro_unicode

Text-to-Speech • Updated 29 days ago
OpenVoiceOS/phoonnx_ar_dii_espeak

Text-to-Speech • Updated 29 days ago

axiomofmind/Moss-image-nsfw-uncensored-lora

Text-to-Image • Updated 13 days ago • 65k • 781

LeRobot & Hugging Face for companies

What LeRobot and the Hugging Face Hub can do for your company: from a first low-cost arm to fine-tuned robot policies.

Running on CPU Upgrade

2

LeRobot for Companies

🤖

2

How LeRobot and Hugging Face help companies start robotics
Running

Robot Setup Advisor

🦾

Right-size a robot, GPU and board; compare cost, energy, CO2
Running

1

LeRobot Presentation

🤖

1

Explore robot learning workflow through an interactive web demo

Geospatial & Location Intelligence

Models, datasets and Spaces for satellite imagery, Earth observation, mapping and location-aware applications.

ibm-esa-geospatial/TerraMind-1.0-base

Updated Nov 3, 2025 • 43.5k • 56
wikimedia/linked-openstreetmap-wikidata-wikipedia-wikivoyage

Viewer • Updated Oct 6 • 50.7M • 644 • 3
Running

Agents

13

Prithvi EO 2.0 Demo

🌎

13

Prithvi-EO-2.0-300M-TL image reconstruction demo
ibm-nasa-geospatial/Prithvi-EO-2.0-600M-TL

Updated Oct 9, 2025 • 1.36k • 17

about 15 hours ago

unsloth/gemma-4-12B-it-qat-GGUF

Any-to-Any • 12B • Updated Jul 17 • 207k • 609
google/gemma-4-26B-A4B-it-qat-q4_0-gguf

Image-Text-to-Text • 25B • Updated Jul 17 • 198k • 218
unsloth/gemma-4-E4B-it-qat-mobile-GGUF

Any-to-Any • 7B • Updated Jul 17 • 48.2k • 36
byteshape/Qwen3.8-27B-GGUF

Image-Text-to-Text • 27B • Updated Sep 18 • 2.06M • 203

axiomofmind/Moss-image-nsfw-uncensored-lora

Text-to-Image • Updated 13 days ago • 65k • 781

Decision Models

convaiinnovations/laya

Text Classification • 0.4B • Updated Oct 3 • 28.5k • • 5.92k

Previous
1
...
536
537
538
539
540
...
24,634
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs