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

sherif1313/Arabic-Qwen3.5-OCR-v4

Image-Text-to-Text • 0.9B • Updated Mar 24 • 355 • 10
sherif1313/Arabic-English-handwritten-OCR-v3

Image-Text-to-Text • 4B • Updated Dec 29, 2025 • 1.95k • 14
sherif1313/Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v3

Image-Text-to-Text • 4B • Updated Dec 30, 2025 • 487 • 1
sherif1313/Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2

Image-to-Text • 4B • Updated Dec 29, 2025 • 13.6k • 12

Very tiny base models

Some very tiny BASE models to see how small models perform on e.g world knowledge

LH-Tech-AI/Quark-v2-0.5M

Text Generation • 466k • Updated May 9 • 65 • 7
LH-Tech-AI/Quark-0.5M

Text Generation • 466k • Updated May 9 • 37 • 2
LH-Tech-AI/Spark-5M-Base-v4

Text Generation • 4.98M • Updated May 2 • 52 • 3
LH-Tech-AI/Crest-20M-Base

Text Generation • Updated Apr 20 • 1

unsloth/Qwen3.6-27B-NVFP4

Image-Text-to-Text • 21B • Updated Jul 12 • 928k • 281
unsloth/Qwen3.6-35B-A3B-NVFP4

Image-Text-to-Text • 25B • Updated Jul 12 • 815k • 122
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast

Image-Text-to-Text • 22B • Updated Jul 12 • 718k • 121
unsloth/Qwen3.6-27B-GGUF

Image-Text-to-Text • 27B • Updated Apr 22 • 675k • 962

1.58-bit Bonsai models

Bonsai Demos

Collection

Demos for Bonsai models • 3 items • Updated Jun 4 • 18
prism-ml/Ternary-Bonsai-8B-mlx-2bit

Text Generation • 8B • Updated Apr 18 • 14.4k • 123
prism-ml/Ternary-Bonsai-4B-mlx-2bit

Text Generation • 4B • Updated Apr 18 • 1.28k • 14
prism-ml/Ternary-Bonsai-1.7B-mlx-2bit

Text Generation • 2B • Updated Apr 18 • 1.78k • 21

Granite 4.1 Language Models

Efficient language models for multilingual generation, coding, RAG, and AI assistant workflows.

ibm-granite/granite-4.1-30b

Text Generation • 29B • Updated May 4 • 254k • 147
ibm-granite/granite-4.1-8b

Text Generation • 9B • Updated May 4 • 158k • 257
ibm-granite/granite-4.1-3b

Text Generation • 3B • Updated May 4 • 561k • 114
ibm-granite/granite-4.1-30b-base

Text Generation • 29B • Updated Apr 28 • 2.9k • 29

Latest Versions of Custom Models used in our Browser AI Assistant

bravesoftware/Ocelot-1-VL

Image-Text-to-Text • Updated Jun 24 • 14 • 21
bravesoftware/Androcles-2

0.1B • Updated 22 days ago • 3 • 2
bravesoftware/Lynx-1-VL

Image-Text-to-Text • Updated 2 days ago • 17 • 2
bravesoftware/Jaguar-1-VL

Image-Text-to-Text • Updated 2 days ago • 16 • 2

Qwen3.6-abliterated

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

Image-Text-to-Text • 36B • Updated Apr 18 • 2.87k • • 96
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

Image-Text-to-Text • 36B • Updated Apr 21 • 120 • 25
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

Text Generation • 36B • Updated Apr 21 • 1.3k • • 218
huihui-ai/Huihui-Qwen3.6-27B-abliterated

Image-Text-to-Text • 28B • Updated Apr 23 • 3.7k • • 74

Mistral AI Audio models.

mistralai/Voxtral-4B-TTS-2603

Text-to-Speech • Updated Mar 31 • 1.75k • 922
mistralai/Voxtral-Mini-4B-Realtime-2602

Automatic Speech Recognition • 4B • Updated Mar 11 • 1.92M • 1.01k
mistralai/Voxtral-Small-24B-2507

Audio-Text-to-Text • 24B • Updated Dec 20, 2025 • 24.9k • 533
mistralai/Voxtral-Mini-3B-2507

5B • Updated Jul 28, 2025 • 169k • 675

Sentence Transformers v5.4 integrations

See https://huggingface.co/blog/multimodal-sentence-transformers

Qwen/Qwen3-Reranker-8B

Text Ranking • 8B • Updated Apr 16 • 411k • 276
Qwen/Qwen3-Reranker-4B

Text Ranking • 4B • Updated Apr 16 • 2.37M • 165
Qwen/Qwen3-Reranker-0.6B

Text Ranking • 0.6B • Updated Apr 16 • 1.54M • 407
Qwen/Qwen3-VL-Embedding-8B

Sentence Similarity • 8B • Updated Apr 16 • 1.5M • 489

Gemma 4 Uncensored

Abliterated Gemma 4 models with refusal behavior removed. Biprojection + EGA for MoE. Cross-validated against 686 prompts from 4 datasets.

TrevorJS/gemma-4-E2B-it-uncensored

Text Generation • 5B • Updated Jun 13 • 15.8k • • 29
TrevorJS/gemma-4-E2B-it-uncensored-GGUF

Text Generation • 5B • Updated Apr 5 • 7.89k • 59
TrevorJS/gemma-4-E4B-it-uncensored

Text Generation • 8B • Updated Jun 13 • 748 • • 40
TrevorJS/gemma-4-E4B-it-uncensored-GGUF

Text Generation • 8B • Updated Apr 5 • 8.69k • 96

sherif1313/Arabic-Qwen3.5-OCR-v4

Image-Text-to-Text • 0.9B • Updated Mar 24 • 355 • 10
sherif1313/Arabic-English-handwritten-OCR-v3

Image-Text-to-Text • 4B • Updated Dec 29, 2025 • 1.95k • 14
sherif1313/Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v3

Image-Text-to-Text • 4B • Updated Dec 30, 2025 • 487 • 1
sherif1313/Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2

Image-to-Text • 4B • Updated Dec 29, 2025 • 13.6k • 12

Latest Versions of Custom Models used in our Browser AI Assistant

bravesoftware/Ocelot-1-VL

Image-Text-to-Text • Updated Jun 24 • 14 • 21
bravesoftware/Androcles-2

0.1B • Updated 22 days ago • 3 • 2
bravesoftware/Lynx-1-VL

Image-Text-to-Text • Updated 2 days ago • 17 • 2
bravesoftware/Jaguar-1-VL

Image-Text-to-Text • Updated 2 days ago • 16 • 2

Very tiny base models

Some very tiny BASE models to see how small models perform on e.g world knowledge

LH-Tech-AI/Quark-v2-0.5M

Text Generation • 466k • Updated May 9 • 65 • 7
LH-Tech-AI/Quark-0.5M

Text Generation • 466k • Updated May 9 • 37 • 2
LH-Tech-AI/Spark-5M-Base-v4

Text Generation • 4.98M • Updated May 2 • 52 • 3
LH-Tech-AI/Crest-20M-Base

Text Generation • Updated Apr 20 • 1

Qwen3.6-abliterated

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

Image-Text-to-Text • 36B • Updated Apr 18 • 2.87k • • 96
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.6-Opus-abliterated

Image-Text-to-Text • 36B • Updated Apr 21 • 120 • 25
huihui-ai/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated

Text Generation • 36B • Updated Apr 21 • 1.3k • • 218
huihui-ai/Huihui-Qwen3.6-27B-abliterated

Image-Text-to-Text • 28B • Updated Apr 23 • 3.7k • • 74

unsloth/Qwen3.6-27B-NVFP4

Image-Text-to-Text • 21B • Updated Jul 12 • 928k • 281
unsloth/Qwen3.6-35B-A3B-NVFP4

Image-Text-to-Text • 25B • Updated Jul 12 • 815k • 122
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast

Image-Text-to-Text • 22B • Updated Jul 12 • 718k • 121
unsloth/Qwen3.6-27B-GGUF

Image-Text-to-Text • 27B • Updated Apr 22 • 675k • 962

Mistral AI Audio models.

mistralai/Voxtral-4B-TTS-2603

Text-to-Speech • Updated Mar 31 • 1.75k • 922
mistralai/Voxtral-Mini-4B-Realtime-2602

Automatic Speech Recognition • 4B • Updated Mar 11 • 1.92M • 1.01k
mistralai/Voxtral-Small-24B-2507

Audio-Text-to-Text • 24B • Updated Dec 20, 2025 • 24.9k • 533
mistralai/Voxtral-Mini-3B-2507

5B • Updated Jul 28, 2025 • 169k • 675

1.58-bit Bonsai models

Bonsai Demos

Collection

Demos for Bonsai models • 3 items • Updated Jun 4 • 18
prism-ml/Ternary-Bonsai-8B-mlx-2bit

Text Generation • 8B • Updated Apr 18 • 14.4k • 123
prism-ml/Ternary-Bonsai-4B-mlx-2bit

Text Generation • 4B • Updated Apr 18 • 1.28k • 14
prism-ml/Ternary-Bonsai-1.7B-mlx-2bit

Text Generation • 2B • Updated Apr 18 • 1.78k • 21

Sentence Transformers v5.4 integrations

See https://huggingface.co/blog/multimodal-sentence-transformers

Qwen/Qwen3-Reranker-8B

Text Ranking • 8B • Updated Apr 16 • 411k • 276
Qwen/Qwen3-Reranker-4B

Text Ranking • 4B • Updated Apr 16 • 2.37M • 165
Qwen/Qwen3-Reranker-0.6B

Text Ranking • 0.6B • Updated Apr 16 • 1.54M • 407
Qwen/Qwen3-VL-Embedding-8B

Sentence Similarity • 8B • Updated Apr 16 • 1.5M • 489

Granite 4.1 Language Models

Efficient language models for multilingual generation, coding, RAG, and AI assistant workflows.

ibm-granite/granite-4.1-30b

Text Generation • 29B • Updated May 4 • 254k • 147
ibm-granite/granite-4.1-8b

Text Generation • 9B • Updated May 4 • 158k • 257
ibm-granite/granite-4.1-3b

Text Generation • 3B • Updated May 4 • 561k • 114
ibm-granite/granite-4.1-30b-base

Text Generation • 29B • Updated Apr 28 • 2.9k • 29

Gemma 4 Uncensored

Abliterated Gemma 4 models with refusal behavior removed. Biprojection + EGA for MoE. Cross-validated against 686 prompts from 4 datasets.

TrevorJS/gemma-4-E2B-it-uncensored

Text Generation • 5B • Updated Jun 13 • 15.8k • • 29
TrevorJS/gemma-4-E2B-it-uncensored-GGUF

Text Generation • 5B • Updated Apr 5 • 7.89k • 59
TrevorJS/gemma-4-E4B-it-uncensored

Text Generation • 8B • Updated Jun 13 • 748 • • 40
TrevorJS/gemma-4-E4B-it-uncensored-GGUF

Text Generation • 8B • Updated Apr 5 • 8.69k • 96

Previous
1
...
37
38
39
40
41
...
23,817
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs