Models
Datasets
Spaces
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

LFM2 is a new generation of hybrid models, designed for on-device deployment.

LiquidAI/LFM2-24B-A2B

Text Generation • 24B • Updated 2 days ago • 10.6k • 223
LiquidAI/LFM2-8B-A1B

Text Generation • 8B • Updated 4 days ago • 45.9k • 326
LiquidAI/LFM2-2.6B-Exp

Text Generation • Updated Jan 5 • 21.5k • 332
LiquidAI/LFM2-2.6B

Text Generation • 3B • Updated 18 days ago • 24.8k • 180

Health AI Developer Foundations (HAI-DEF)

Groups models released for use in health AI by Google. Read more about HAI-DEF at http://goo.gle/hai-def

google/medgemma-27b-it

Image-Text-to-Text • Updated Jul 10, 2025 • 32.6k • 316
google/medgemma-27b-text-it

Text Generation • Updated Sep 16, 2025 • 45.9k • 408
google/medgemma-4b-pt

Image-Text-to-Text • Updated Sep 16, 2025 • 12.2k • 144
google/medgemma-4b-it

Image-Text-to-Text • Updated Oct 28, 2025 • 202k • 907

Efficient MoE-based LLM

Mixture-of-Experts Large Language Models with Advanced Quantization

nota-ai/Solar-Open-100B-Nota-FP8

Text Generation • Updated Jan 26 • 204 • 31
nota-ai/Solar-Open-100B-NotaMoEQuant-Int4

Text Generation • Updated Jan 26 • 3.11k • 42
nota-ai/Qwen3-30B-A3B-NotaMoEQuant-Int4

Text Generation • 0.6B • Updated Jan 16 • 8 • 8
nota-ai/GLM-4.5-Air-NotaMoeQuant-Int4

Text Generation • 1B • Updated Dec 29, 2025 • 10 • 6

JoyAI-LLM Flash

jdopensource/JoyAI-LLM-Flash

Text Generation • 49B • Updated 4 days ago • 1.41k • 157
jdopensource/JoyAI-LLM-Flash-Base

Text Generation • 49B • Updated 16 days ago • 85 • 21
jdopensource/JoyAI-LLM-Flash-FP8

Text Generation • 49B • Updated 5 days ago • 142 • 4
jdopensource/JoyAI-LLM-Flash-INT4

Text Generation • 10B • Updated 4 days ago • 31 • 2

Transformers.js V4 demos

A collection of demos built with Transformers.js V4

Running

Featured

57

GPT OSS WebGPU

⚡

57

Run GPT-OSS-20B locally in your browser on WebGPU
Running

47

LFM2.5 1.2B Thinking WebGPU

💧

47

Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
Running

28

SAM3 Tracker WebGPU

🎯

28

Segment images with click points and download cutouts
Running

20

TranslateGemma 4B WebGPU

🌐

20

Private browser-based translator with 56 languages

facebook/SACo-Gold

Viewer • Updated Nov 17, 2025 • 21 • 123 • 8
facebook/SACo-Silver

Viewer • Updated Nov 17, 2025 • 9 • 52
facebook/SACo-VEval

Viewer • Updated Nov 17, 2025 • 2 • 50 • 1
facebook/SA-FARI

Updated Nov 19, 2025 • 45 • 12

The third generation of our Danish ASR and TTS models.

CoRal-project/roest-v3-whisper-1.5b

Automatic Speech Recognition • 2B • Updated 3 days ago • 196 • 4
CoRal-project/roest-v3-wav2vec2-315m

Automatic Speech Recognition • 0.3B • Updated 4 days ago • 133 • 2
CoRal-project/roest-v3-chatterbox-500m

Text-to-Speech • Updated 4 days ago • 28 • 3
CoRal-project/roest-v3-chatterbox-350m

Text-to-Speech • Updated 4 days ago • 2

Efficient Large Vision-Language Model

ERGO: LVLM trained with RL on efficiency objectives; https://github.com/nota-github/ERGO

nota-ai/ERGO-7B

Image-Text-to-Text • 8B • Updated 5 days ago • 485 • 15
nota-ai/phiva-4b-hf

Image-Text-to-Text • 4B • Updated Oct 4, 2024 • 3 • 3
nota-ai/phiva-4b-hf-q4f16_1-MLC

Updated Aug 16, 2024

zai-org/GLM-5

Text Generation • 754B • Updated 17 days ago • 194k • • 1.67k
zai-org/GLM-5-FP8

Text Generation • Updated 17 days ago • 873k • 122

Collection of Instruct, Base, and Japanese LFM2.5-1.2B models.

LiquidAI/LFM2.5-1.2B-Thinking

Text Generation • Updated 28 days ago • 38.9k • 302
LiquidAI/LFM2.5-1.2B-Instruct

Text Generation • 1B • Updated 6 days ago • 110k • 510
LiquidAI/LFM2.5-1.2B-JP

Text Generation • 1B • Updated Jan 6 • 6.6k • 139
LiquidAI/LFM2.5-1.2B-Base

Text Generation • Updated Jan 22 • 14.8k • 113

LFM2 is a new generation of hybrid models, designed for on-device deployment.

LiquidAI/LFM2-24B-A2B

Text Generation • 24B • Updated 2 days ago • 10.6k • 223
LiquidAI/LFM2-8B-A1B

Text Generation • 8B • Updated 4 days ago • 45.9k • 326
LiquidAI/LFM2-2.6B-Exp

Text Generation • Updated Jan 5 • 21.5k • 332
LiquidAI/LFM2-2.6B

Text Generation • 3B • Updated 18 days ago • 24.8k • 180

facebook/SACo-Gold

Viewer • Updated Nov 17, 2025 • 21 • 123 • 8
facebook/SACo-Silver

Viewer • Updated Nov 17, 2025 • 9 • 52
facebook/SACo-VEval

Viewer • Updated Nov 17, 2025 • 2 • 50 • 1
facebook/SA-FARI

Updated Nov 19, 2025 • 45 • 12

Health AI Developer Foundations (HAI-DEF)

Groups models released for use in health AI by Google. Read more about HAI-DEF at http://goo.gle/hai-def

google/medgemma-27b-it

Image-Text-to-Text • Updated Jul 10, 2025 • 32.6k • 316
google/medgemma-27b-text-it

Text Generation • Updated Sep 16, 2025 • 45.9k • 408
google/medgemma-4b-pt

Image-Text-to-Text • Updated Sep 16, 2025 • 12.2k • 144
google/medgemma-4b-it

Image-Text-to-Text • Updated Oct 28, 2025 • 202k • 907

The third generation of our Danish ASR and TTS models.

CoRal-project/roest-v3-whisper-1.5b

Automatic Speech Recognition • 2B • Updated 3 days ago • 196 • 4
CoRal-project/roest-v3-wav2vec2-315m

Automatic Speech Recognition • 0.3B • Updated 4 days ago • 133 • 2
CoRal-project/roest-v3-chatterbox-500m

Text-to-Speech • Updated 4 days ago • 28 • 3
CoRal-project/roest-v3-chatterbox-350m

Text-to-Speech • Updated 4 days ago • 2

Efficient MoE-based LLM

Mixture-of-Experts Large Language Models with Advanced Quantization

nota-ai/Solar-Open-100B-Nota-FP8

Text Generation • Updated Jan 26 • 204 • 31
nota-ai/Solar-Open-100B-NotaMoEQuant-Int4

Text Generation • Updated Jan 26 • 3.11k • 42
nota-ai/Qwen3-30B-A3B-NotaMoEQuant-Int4

Text Generation • 0.6B • Updated Jan 16 • 8 • 8
nota-ai/GLM-4.5-Air-NotaMoeQuant-Int4

Text Generation • 1B • Updated Dec 29, 2025 • 10 • 6

Efficient Large Vision-Language Model

ERGO: LVLM trained with RL on efficiency objectives; https://github.com/nota-github/ERGO

nota-ai/ERGO-7B

Image-Text-to-Text • 8B • Updated 5 days ago • 485 • 15
nota-ai/phiva-4b-hf

Image-Text-to-Text • 4B • Updated Oct 4, 2024 • 3 • 3
nota-ai/phiva-4b-hf-q4f16_1-MLC

Updated Aug 16, 2024

JoyAI-LLM Flash

jdopensource/JoyAI-LLM-Flash

Text Generation • 49B • Updated 4 days ago • 1.41k • 157
jdopensource/JoyAI-LLM-Flash-Base

Text Generation • 49B • Updated 16 days ago • 85 • 21
jdopensource/JoyAI-LLM-Flash-FP8

Text Generation • 49B • Updated 5 days ago • 142 • 4
jdopensource/JoyAI-LLM-Flash-INT4

Text Generation • 10B • Updated 4 days ago • 31 • 2

zai-org/GLM-5

Text Generation • 754B • Updated 17 days ago • 194k • • 1.67k
zai-org/GLM-5-FP8

Text Generation • Updated 17 days ago • 873k • 122

Transformers.js V4 demos

A collection of demos built with Transformers.js V4

Running

Featured

57

GPT OSS WebGPU

⚡

57

Run GPT-OSS-20B locally in your browser on WebGPU
Running

47

LFM2.5 1.2B Thinking WebGPU

💧

47

Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
Running

28

SAM3 Tracker WebGPU

🎯

28

Segment images with click points and download cutouts
Running

20

TranslateGemma 4B WebGPU

🌐

20

Private browser-based translator with 56 languages

Collection of Instruct, Base, and Japanese LFM2.5-1.2B models.

LiquidAI/LFM2.5-1.2B-Thinking

Text Generation • Updated 28 days ago • 38.9k • 302
LiquidAI/LFM2.5-1.2B-Instruct

Text Generation • 1B • Updated 6 days ago • 110k • 510
LiquidAI/LFM2.5-1.2B-JP

Text Generation • 1B • Updated Jan 6 • 6.6k • 139
LiquidAI/LFM2.5-1.2B-Base

Text Generation • Updated Jan 22 • 14.8k • 113

Previous
1
2
3
4
5
...
18,650
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs