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

Collections

Discover the best community collections!

Collections trending this week

Wouldn't it be great if your LLMs can make calibrated decisions with one switch on the API.

GreenPT/metis-hybrid-4b-Q4_K_M-GGUF

4B • Updated 24 days ago • 30
GreenPT/metis-hybrid-4b-Q8_0-GGUF

4B • Updated 24 days ago • 21
GreenPT/metis-hybrid-9b

Updated 24 days ago • 38
GreenPT/metis-hybrid-27b

Updated 24 days ago • 24

Encoder comparison after equivalent retrieval fine-tuning

ModernBERT, Ettin and UltraBERT: 54 retrieval models, frozen data and results. Validation-selected models first. Matched training, one seed.

tomaarsen/encoder-comparison-20261014

38.2 MB
tomaarsen/encoder-comparison-20261014

Updated 25 days ago • 6.29k
tomaarsen/modernbert-base-dense-msmarco32k-1e-4-20261014

Sentence Similarity • 0.1B • Updated 25 days ago • 40
tomaarsen/modernbert-base-multivector-msmarco32k-3e-4-20261014

Feature Extraction • 0.1B • Updated 25 days ago • 37

Collection of lightweight models

GoudaAI/Cheddar-2.0

Text Generation • 0.3B • Updated 25 days ago • 518 • 1
GoudaAI/Cheddar-2.0-Instruct

Text Generation • 0.3B • Updated 25 days ago • 465 • 1
GoudaAI/Gouda-2.0

Text Generation • 0.1B • Updated 25 days ago • 364
GoudaAI/Gouda-2.0-Instruct

Text Generation • 0.1B • Updated 25 days ago • 156

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 26 days ago • 5.23M • 4.97k

kyutai/moshiko-pytorch-bf16

8B • Updated Sep 18, 2024 • 280k • 265

Muse Glimmer NVFP4 W4A16 development conversion. Vision stays at source precision. Not quality-certified.

AutomatosX/AX-Muse-Glimmer-30B-CUDA-AXQ-NVFP4-W4A16

Image-Text-to-Text • 30B • Updated 25 days ago • 67
AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-6bit

Text Generation • 30B • Updated 15 days ago • 204

huiwon/fred-wan22-5b-droid

Updated 28 days ago
huiwon/fred-wan21-14b-droid

Updated 28 days ago

AXQ Reference Storage

Low-precision reference storage, including source-layout MX matrices. See reconstruction and runtime limits in each card; not quality-certified.

AutomatosX/AX-Image-2.1-Turbo-AXQ-NVFP4

Text-to-Image • Updated 25 days ago • 27
AutomatosX/AX-Unlimited-OCR-2-AXQ-MXFP4

3B • Updated 12 days ago • 48
AutomatosX/AX-Unlimited-OCR-2-AXQ-MXFP8

3B • Updated 12 days ago • 48

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Paper • 2610.13166 • Published about 1 month ago • 126

pyannote/speaker-diarization-community-1

Automatic Speech Recognition • Updated Sep 29, 2025 • 5.13M • 3.99k

Wouldn't it be great if your LLMs can make calibrated decisions with one switch on the API.

GreenPT/metis-hybrid-4b-Q4_K_M-GGUF

4B • Updated 24 days ago • 30
GreenPT/metis-hybrid-4b-Q8_0-GGUF

4B • Updated 24 days ago • 21
GreenPT/metis-hybrid-9b

Updated 24 days ago • 38
GreenPT/metis-hybrid-27b

Updated 24 days ago • 24

Muse Glimmer NVFP4 W4A16 development conversion. Vision stays at source precision. Not quality-certified.

AutomatosX/AX-Muse-Glimmer-30B-CUDA-AXQ-NVFP4-W4A16

Image-Text-to-Text • 30B • Updated 25 days ago • 67
AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-6bit

Text Generation • 30B • Updated 15 days ago • 204

Encoder comparison after equivalent retrieval fine-tuning

ModernBERT, Ettin and UltraBERT: 54 retrieval models, frozen data and results. Validation-selected models first. Matched training, one seed.

tomaarsen/encoder-comparison-20261014

38.2 MB
tomaarsen/encoder-comparison-20261014

Updated 25 days ago • 6.29k
tomaarsen/modernbert-base-dense-msmarco32k-1e-4-20261014

Sentence Similarity • 0.1B • Updated 25 days ago • 40
tomaarsen/modernbert-base-multivector-msmarco32k-3e-4-20261014

Feature Extraction • 0.1B • Updated 25 days ago • 37

huiwon/fred-wan22-5b-droid

Updated 28 days ago
huiwon/fred-wan21-14b-droid

Updated 28 days ago

Collection of lightweight models

GoudaAI/Cheddar-2.0

Text Generation • 0.3B • Updated 25 days ago • 518 • 1
GoudaAI/Cheddar-2.0-Instruct

Text Generation • 0.3B • Updated 25 days ago • 465 • 1
GoudaAI/Gouda-2.0

Text Generation • 0.1B • Updated 25 days ago • 364
GoudaAI/Gouda-2.0-Instruct

Text Generation • 0.1B • Updated 25 days ago • 156

AXQ Reference Storage

Low-precision reference storage, including source-layout MX matrices. See reconstruction and runtime limits in each card; not quality-certified.

AutomatosX/AX-Image-2.1-Turbo-AXQ-NVFP4

Text-to-Image • Updated 25 days ago • 27
AutomatosX/AX-Unlimited-OCR-2-AXQ-MXFP4

3B • Updated 12 days ago • 48
AutomatosX/AX-Unlimited-OCR-2-AXQ-MXFP8

3B • Updated 12 days ago • 48

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 26 days ago • 5.23M • 4.97k

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Paper • 2610.13166 • Published about 1 month ago • 126

kyutai/moshiko-pytorch-bf16

8B • Updated Sep 18, 2024 • 280k • 265

pyannote/speaker-diarization-community-1

Automatic Speech Recognition • Updated Sep 29, 2025 • 5.13M • 3.99k

Previous
1
...
790
791
792
793
794
...
24,675
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs