Qwen/Qwen2.5-Omni-7B
Any-to-Any • 11B • Updated • 424k • 1.92k
Vision Language Models: 2025 Update
This collection includes all the models, datasets and Spaces mentioned in the blog Vision Language Models: 2025 Update
-
-
Qwen2.5 Omni 7B Demo
🏆374Chat with text, audio, images, and video, get spoken replies
-
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 174 -
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 383k • 1.3k -
deepseek-ai/Janus-Pro-7B
Any-to-Any • Updated • 11k • 3.64k -
Chat With Janus-Pro-7B
🌍2.02kA unified multimodal understanding and generation model.
-
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Paper • 2501.17811 • Published • 11 -
Qwen/QVQ-72B-Preview
Image-Text-to-Text • 73B • Updated • 927 • 610 -
moonshotai/Kimi-VL-A3B-Thinking
Image-Text-to-Text • 16B • Updated • 165k • 449 -
Chat with Kimi-VL-A3B-Thinking-2506
🤔202Chat with images, videos, PDFs and get thoughtful responses
-
Kimi-VL Technical Report
Paper • 2504.07491 • Published • 142 -
moonshotai/MoonViT-SO-400M
Image Feature Extraction • 0.4B • Updated • 5.56k • 87 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • 0.9B • Updated • 2.28M • 681 -
moonshotai/Kimi-VL-A3B-Instruct
Image-Text-to-Text • 16B • Updated • 386k • 275 -
HuggingFaceTB/SmolVLM-Instruct
Image-Text-to-Text • 2B • Updated • 24k • 591 -
SmolVLM
📊143Answer questions about images with AI chat
-
HuggingFaceTB/SmolVLM2-2.2B-Instruct
Image-Text-to-Text • 2B • Updated • 290k • 327 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 210 -
SmolVLM
📊81Ask questions about images or videos and get answers
-
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 854k • • 2k -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 13.6k • 207 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 221 • 400 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • 109B • Updated • 462k • • 1.33k -
meta-llama/Llama-4-Maverick-17B-128E-Instruct
Image-Text-to-Text • 402B • Updated • 55.6k • 504 -
MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
Paper • 2401.15947 • Published • 54 -
deepseek-ai/deepseek-vl2
Image-Text-to-Text • 27B • Updated • 2.41k • 387 -
Chat with DeepSeek-VL2-small
🌍609Chat with an AI using text and images for visual answers
-
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Paper • 2412.10302 • Published • 24 -
lerobot/pi0_old
Robotics • 4B • Updated • 734 • 309 -
nvidia/GR00T-N1-2B
Robotics • 2B • Updated • 286 • 355 -
google/paligemma-3b-pt-224
Image-Text-to-Text • 3B • Updated • 164k • 519 -
PaliGemma: A versatile 3B VLM for transfer
Paper • 2407.07726 • Published • 73 -
PaliGemma Demo
🤲314Annotate and describe images with text prompts
-
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 136 -
Paligemma2 Mix
🌖98Generate text answers or segment objects from images
-
google/paligemma2-10b-mix-448
Image-Text-to-Text • 10B • Updated • 9.88k • 36 -
allenai/Molmo-72B-0924
Image-Text-to-Text • 73B • Updated • 3.61k • 299 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 123 -
Qwen/Qwen2.5-VL-72B-Instruct
Image-Text-to-Text • 73B • Updated • 567k • • 643 -
Qwen2.5-VL Technical Report
Paper • 2502.13923 • Published • 218 -
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 6.49k • 166 -
ShieldGemma 2: Robust and Tractable Image Content Moderation
Paper • 2504.01081 • Published • 3 -
ShieldGemma2 VLM
📉12Demo for ShieldGemma 2, multimodal safety model
-
meta-llama/Llama-Guard-4-12B
Image-Text-to-Text • 12B • Updated • 191k • • 115 -
Llama Guard 4
🦀1Check if text and images are safe
-
marco/mcdse-2b-v1
2B • Updated • 58 • 56 -
vidore/colpali-v1.3
Visual Document Retrieval • Updated • 15.5k • 99 -
ColPali: Efficient Document Retrieval with Vision Language Models
Paper • 2407.01449 • Published • 51 -
vidore/colqwen2.5-v0.2
Visual Document Retrieval • Updated • 48.2k • 99 -
vidore/colsmolvlm-v0.1
Visual Document Retrieval • Updated • 191 • 55 -
Qwen/Qwen2.5-VL-32B-Instruct
Image-Text-to-Text • 33B • Updated • 738k • • 498 -
Qwen2.5 VL 32B Instruct Demo
🏃170Chat with a multimodal AI using text, images, or video
-
Vision-CAIR/LongVU_Qwen2_7B
Video-Text-to-Text • 8B • Updated • 298 • 76 -
LongVU
🌖91Answer questions about uploaded videos or images
-
openbmb/RLAIF-V-Dataset
Viewer • Updated • 83.1k • 1.71k • 216 -
HuggingFaceH4/rlaif-v_formatted
Viewer • Updated • 83.1k • 357 • 17 -
MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Paper • 2404.16006 • Published • 2 -
Kaining/MMT-Bench
Viewer • Updated • 30k • 138 • 11 -
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Paper • 2409.02813 • Published • 34 -
MMMU/MMMU_Pro
Benchmark • Updated • 5.19k • 12.6k • 65 -
reducto/RolmOCR
Image-Text-to-Text • 8B • Updated • 241k • 589 -
Alpha-VLLM/Lumina-mGPT-7B-768
Any-to-Any • 7B • Updated • 666 • 39 -
facebook/chameleon-7b
Image-Text-to-Text • 7B • Updated • 222k • 202