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

sparkarena/Minimax-M3-v0-NVFP4

Image-Text-to-Text • 242B • Updated Jun 15 • 31.3k • 15
sparkarena/Minimax-M3-v0-NVFP4-REAP50

Image-Text-to-Text • 125B • Updated Jun 15 • 979 • 12
sparkarena/Minimax-M3-v0-NVFP4-REAP25

Image-Text-to-Text • 184B • Updated Jun 13 • 804 • 1

google/diffusiongemma-26B-A4B-it

Image-Text-to-Text • 26B • Updated 18 days ago • 2.01M • 1.16k

AI Porn Generators

Discover the best AI porn sites 2026 — tested & handpicked. AI porn generator, chat, maker for pics, gifs & video. no login, no blur, free credits

The largest public dataset with sensitive private information

nvidia/Privasis-Zero

Viewer • Updated Mar 30 • 1.3M • 163 • 12
nvidia/Privasis-Cleaner-0.6B

Text Generation • 0.6B • Updated Jun 29 • 550 • 18
nvidia/Privasis-Cleaner-4B

Text Generation • 4B • Updated Jun 29 • 436 • 10
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch

Paper • 2602.03183 • Published Feb 3 • 13

Open-sourced models and datasets for training the chess reasoning models.

about 13 hours ago

pavelslab-nyu/pretrain_v1_54B

Updated 14 days ago • 2.65k • 1
pavelslab-nyu/chess_puzzle_benchmark

Viewer • Updated 14 days ago • 2.36k • 744
pre-to-post-olmo/Math-Models

Text Generation • Updated 14 days ago
pavelslab-nyu/chess_puzzle_training_datasets

Viewer • Updated Jun 8 • 229k • 52

Open ASR Leaderboard Eval Configurations

Running

1

Open ASR Leaderboard configuration for Transformers 🤗 models

🎙

1

Run evaluation of text normalization models
Running

1

Open ASR Leaderboard configuration for NVIDIA NeMo ASR models

🎙

1

Normalize text to a consistent, clean format
Running

Open ASR Leaderboard configuration for Boson's Higgs Audio v3

🎙

Normalize and clean text data for analysis
Sleeping

Open ASR Leaderboard configuration for API models

🎙

Run model evaluation and get performance metrics

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks

PaddlePaddle/PP-OCRv6_medium_det_safetensors

Image-to-Text • 22M • Updated Jun 12 • 1.83k • 118
PaddlePaddle/PP-OCRv6_small_det_safetensors

Image-to-Text • 2.48M • Updated Jun 12 • 552 • 25
PaddlePaddle/PP-OCRv6_tiny_det_safetensors

Image-to-Text • 438k • Updated Jun 12 • 234 • 27
PaddlePaddle/PP-OCRv6_medium_rec_safetensors

Image-to-Text • 19.2M • Updated Jun 12 • 1.4k • 24

jedisct1/Qwen3.6-35B-rust-v2-MTP-bf16.mlx

35B • Updated Jun 8 • 89
jedisct1/Qwen3.6-35B-rust-v2-MTP-4bit.mlx

35B • Updated Jun 8 • 63
jedisct1/Qwen3.6-35B-rust-v2-MTP-8bit.mlx

35B • Updated Jun 8 • 42
jedisct1/Qwen3.6-35B-rust-v2-bf16.mlx

35B • Updated Jun 8 • 61

Sapiens2 INT4-G128 Quantized Checkpoints

All 22 Sapiens2 INT4-G128 quants with fidelity scores.

Reza2kn/sapiens2-matting-1b-INT4-G128

Updated Jun 8
Reza2kn/sapiens2-normal-0.4b-INT4-G128

Updated Jun 8
Reza2kn/sapiens2-normal-0.8b-INT4-G128

Updated Jun 8
Reza2kn/sapiens2-normal-1b-INT4-G128

Updated Jun 8

Native Multimodal Model Zoo

Native Multimodal Model Zoo is a curated collection of native multimodal models for seamless understanding and generation across diverse modalities.

BAAI/Emu3.5

Any-to-Any • 34B • Updated Dec 25, 2025 • 678 • 173
sensenova/SenseNova-U1-8B-MoT

Any-to-Any • 18B • Updated May 15 • 28.6k • 290
bytedance-research/Lance

Any-to-Any • Updated May 28 • 431 • 1.06k
lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct

Image-Text-to-Text • 9B • Updated 17 days ago • 86.9k • 13

sparkarena/Minimax-M3-v0-NVFP4

Image-Text-to-Text • 242B • Updated Jun 15 • 31.3k • 15
sparkarena/Minimax-M3-v0-NVFP4-REAP50

Image-Text-to-Text • 125B • Updated Jun 15 • 979 • 12
sparkarena/Minimax-M3-v0-NVFP4-REAP25

Image-Text-to-Text • 184B • Updated Jun 13 • 804 • 1

Open ASR Leaderboard Eval Configurations

Running

1

Open ASR Leaderboard configuration for Transformers 🤗 models

🎙

1

Run evaluation of text normalization models
Running

1

Open ASR Leaderboard configuration for NVIDIA NeMo ASR models

🎙

1

Normalize text to a consistent, clean format
Running

Open ASR Leaderboard configuration for Boson's Higgs Audio v3

🎙

Normalize and clean text data for analysis
Sleeping

Open ASR Leaderboard configuration for API models

🎙

Run model evaluation and get performance metrics

google/diffusiongemma-26B-A4B-it

Image-Text-to-Text • 26B • Updated 18 days ago • 2.01M • 1.16k

From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks

PaddlePaddle/PP-OCRv6_medium_det_safetensors

Image-to-Text • 22M • Updated Jun 12 • 1.83k • 118
PaddlePaddle/PP-OCRv6_small_det_safetensors

Image-to-Text • 2.48M • Updated Jun 12 • 552 • 25
PaddlePaddle/PP-OCRv6_tiny_det_safetensors

Image-to-Text • 438k • Updated Jun 12 • 234 • 27
PaddlePaddle/PP-OCRv6_medium_rec_safetensors

Image-to-Text • 19.2M • Updated Jun 12 • 1.4k • 24

AI Porn Generators

Discover the best AI porn sites 2026 — tested & handpicked. AI porn generator, chat, maker for pics, gifs & video. no login, no blur, free credits

jedisct1/Qwen3.6-35B-rust-v2-MTP-bf16.mlx

35B • Updated Jun 8 • 89
jedisct1/Qwen3.6-35B-rust-v2-MTP-4bit.mlx

35B • Updated Jun 8 • 63
jedisct1/Qwen3.6-35B-rust-v2-MTP-8bit.mlx

35B • Updated Jun 8 • 42
jedisct1/Qwen3.6-35B-rust-v2-bf16.mlx

35B • Updated Jun 8 • 61

The largest public dataset with sensitive private information

nvidia/Privasis-Zero

Viewer • Updated Mar 30 • 1.3M • 163 • 12
nvidia/Privasis-Cleaner-0.6B

Text Generation • 0.6B • Updated Jun 29 • 550 • 18
nvidia/Privasis-Cleaner-4B

Text Generation • 4B • Updated Jun 29 • 436 • 10
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch

Paper • 2602.03183 • Published Feb 3 • 13

Sapiens2 INT4-G128 Quantized Checkpoints

All 22 Sapiens2 INT4-G128 quants with fidelity scores.

Reza2kn/sapiens2-matting-1b-INT4-G128

Updated Jun 8
Reza2kn/sapiens2-normal-0.4b-INT4-G128

Updated Jun 8
Reza2kn/sapiens2-normal-0.8b-INT4-G128

Updated Jun 8
Reza2kn/sapiens2-normal-1b-INT4-G128

Updated Jun 8

Open-sourced models and datasets for training the chess reasoning models.

about 13 hours ago

pavelslab-nyu/pretrain_v1_54B

Updated 14 days ago • 2.65k • 1
pavelslab-nyu/chess_puzzle_benchmark

Viewer • Updated 14 days ago • 2.36k • 744
pre-to-post-olmo/Math-Models

Text Generation • Updated 14 days ago
pavelslab-nyu/chess_puzzle_training_datasets

Viewer • Updated Jun 8 • 229k • 52

Native Multimodal Model Zoo

Native Multimodal Model Zoo is a curated collection of native multimodal models for seamless understanding and generation across diverse modalities.

BAAI/Emu3.5

Any-to-Any • 34B • Updated Dec 25, 2025 • 678 • 173
sensenova/SenseNova-U1-8B-MoT

Any-to-Any • 18B • Updated May 15 • 28.6k • 290
bytedance-research/Lance

Any-to-Any • Updated May 28 • 431 • 1.06k
lmms-lab-encoder/LLaVA-OneVision-2-8B-Instruct

Image-Text-to-Text • 9B • Updated 17 days ago • 86.9k • 13

Previous
1
...
24
25
26
27
28
...
22,210
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs