Qwen/Qwen2.5-Omni-7B
Any-to-Any
•
11B
•
Updated
•
105k
•
1.71k
Vision Language Models: 2025 Update
This collection includes all the models, datasets and Spaces mentioned in the blog Vision Language Models: 2025 Update
-
-
330
Qwen2.5 Omni 7B Demo
🏆Interact with Qwen using text, audio, video, or images
-
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 164 -
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 90.8k • 1.2k -
deepseek-ai/Janus-Pro-7B
Any-to-Any • Updated • 118k • 3.46k -
1.99k
Chat With Janus-Pro-7B
🌍A unified multimodal understanding and generation model.
-
Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
Paper • 2501.17811 • Published • 6 -
Qwen/QVQ-72B-Preview
Image-Text-to-Text • 73B • Updated • 35.4k • 598 -
moonshotai/Kimi-VL-A3B-Thinking
Image-Text-to-Text • 16B • Updated • 128k • 429 -
158
Chat with Kimi-VL-A3B-Thinking-2506
🤔Chat with images, videos, or PDFs to generate text
-
Kimi-VL Technical Report
Paper • 2504.07491 • Published • 133 -
moonshotai/MoonViT-SO-400M
Image Feature Extraction • 0.4B • Updated • 128 • 18 -
google/siglip-so400m-patch14-384
Zero-Shot Image Classification • 0.9B • Updated • 1.85M • 575 -
moonshotai/Kimi-VL-A3B-Instruct
Image-Text-to-Text • 16B • Updated • 182k • 217 -
HuggingFaceTB/SmolVLM-Instruct
Image-Text-to-Text • 2B • Updated • 120k • 518 -
142
SmolVLM
📊Ask questions about images to get answers
-
HuggingFaceTB/SmolVLM2-2.2B-Instruct
Image-Text-to-Text • 2B • Updated • 68.7k • 223 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 193 -
79
SmolVLM
📊Answer questions using images or videos
-
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 324k • • 1.51k -
unsloth/gemma-3-27b-it-GGUF
Image-Text-to-Text • 27B • Updated • 29.8k • 140 -
google/gemma-3-27b-it-qat-q4_0-gguf
Image-Text-to-Text • 27B • Updated • 7.19k • 315 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • 109B • Updated • 596k • • 1.02k -
meta-llama/Llama-4-Maverick-17B-128E-Instruct
Image-Text-to-Text • 402B • Updated • 34.2k • • 380 -
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 • 8.55k • 348 -
507
Chat with DeepSeek-VL2-small
🌍Generate responses using images and text input
-
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Paper • 2412.10302 • Published • 18 -
lerobot/pi0
Robotics • 4B • Updated • 14.8k • 279 -
lerobot/pi0fast_base
Robotics • 3B • Updated • 1.67k • 24 -
nvidia/GR00T-N1-2B
Robotics • 2B • Updated • 2.14k • 323 -
google/paligemma-3b-pt-224
Image-Text-to-Text • 3B • Updated • 38.8k • 340 -
PaliGemma: A versatile 3B VLM for transfer
Paper • 2407.07726 • Published • 72 -
313
PaliGemma Demo
🤲Annotate and describe images with text prompts
-
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 134 -
91
Paligemma2 Mix
🌖Generate text or segment objects from an image
-
google/paligemma2-10b-mix-448
Image-Text-to-Text • 10B • Updated • 3.98k • 31 -
allenai/Molmo-72B-0924
Image-Text-to-Text • 73B • Updated • 2.29k • 286 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 122 -
Qwen/Qwen2.5-VL-72B-Instruct
Image-Text-to-Text • 73B • Updated • 381k • • 515 -
Qwen2.5-VL Technical Report
Paper • 2502.13923 • Published • 197 -
google/shieldgemma-2-4b-it
Image-Text-to-Text • 4B • Updated • 138k • 116 -
ShieldGemma 2: Robust and Tractable Image Content Moderation
Paper • 2504.01081 • Published • 3 -
12
ShieldGemma2 VLM
📉Demo for ShieldGemma 2, multimodal safety model
-
meta-llama/Llama-Guard-4-12B
Image-Text-to-Text • 12B • Updated • 16.8k • • 50 -
Llama Guard 4
🦀Check if text and images are safe
-
254
Qwen2.5 VL 72B Instruct
💻Chat with Qwen2.5-VL-72B using text and files
-
marco/mcdse-2b-v1
2B • Updated • 2.9k • 56 -
vidore/colpali-v1.3
Visual Document Retrieval • Updated • 342k • 63 -
ColPali: Efficient Document Retrieval with Vision Language Models
Paper • 2407.01449 • Published • 50 -
vidore/colqwen2.5-v0.2
Visual Document Retrieval • Updated • 41.8k • 57 -
vidore/colsmolvlm-v0.1
Visual Document Retrieval • Updated • 2.04k • 52 -
Qwen/Qwen2.5-VL-32B-Instruct
Image-Text-to-Text • 33B • Updated • 465k • • 408 -
141
Qwen2.5 VL 32B Instruct Demo
🏃Chat with images and videos using Qwen
-
Vision-CAIR/LongVU_Qwen2_7B
Video-Text-to-Text • 8B • Updated • 258 • 72 -
83
LongVU
🌖Generate responses to video or image inputs
-
openbmb/RLAIF-V-Dataset
Viewer • Updated • 74.8k • 1.92k • 178 -
HuggingFaceH4/rlaif-v_formatted
Viewer • Updated • 83.1k • 794 • 10 -
MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Paper • 2404.16006 • Published -
Kaining/MMT-Bench
Viewer • Updated • 30k • 74 • 10 -
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
Paper • 2409.02813 • Published • 32 -
MMMU/MMMU_Pro
Viewer • Updated • 5.19k • 4.92k • 29 -
reducto/RolmOCR
Image-to-Text • 8B • Updated • 180k • 455 -
Alpha-VLLM/Lumina-mGPT-7B-768
Any-to-Any • 7B • Updated • 4.02k • 36 -
facebook/chameleon-7b
Image-Text-to-Text • 7B • Updated • 35.9k • 185