OpenGVLab/InternVL3-1B
Image-Text-to-Text • 0.9B • Updated • 132k • 82
🤏🏾 VLMs & LLMs
My favorite small LLMs and VLMs.
-
-
vikhyatk/moondream2
Image-Text-to-Text • 2B • Updated • 2.47M • 1.41k -
microsoft/Florence-2-base
Image-Text-to-Text • 0.2B • Updated • 547k • 363 -
HuggingFaceTB/SmolVLM2-256M-Video-Instruct
Image-Text-to-Text • 0.3B • Updated • 124k • 101 -
facebook/Perception-LM-1B
Image-Text-to-Text • 2B • Updated • 5.81k • 45 -
AIDC-AI/Ovis2-1B
Image-Text-to-Text • 1B • Updated • 44.3k • 96 -
FastVLM: Efficient Vision Encoding for Vision Language Models
Paper • 2412.13303 • Published • 75 -
HuggingFaceTB/SmolLM2-135M-Instruct
Text Generation • 0.1B • Updated • 806k • 309 -
facebook/MobileLLM-125M
Text Generation • Updated • 1.47k • 131 -
deepseek-ai/Janus-Pro-1B
Any-to-Any • Updated • 15.4k • 474 -
Qwen/Qwen2.5-Omni-3B
Any-to-Any • Updated • 520k • 332 -
Qwen/Qwen2.5-0.5B-Instruct
Text Generation • 0.5B • Updated • 5.82M • 500 -
h2oai/h2ovl-mississippi-800m
Text Generation • 0.8B • Updated • 950k • 39 -
HuggingFaceTB/SmolLM3-3B
Text Generation • 3B • Updated • 157k • 937 -
google/gemma-3-1b-it
Text Generation • 1.0B • Updated • 620k • 929 -
microsoft/Phi-4-mini-instruct
Text Generation • Updated • 1.34M • 726