125
Ovis2 16B
🦫
See, read, and reason—better together.
Ovis2
Our latest advancement in multi-modal large language models (MLLMs)
-
-
20
Ovis2 1B
🦫Small model can do big things.
-
AIDC-AI/Ovis2-1B
Image-Text-to-Text • 1B • Updated • 4.04k • 96 -
AIDC-AI/Ovis2-2B
Image-Text-to-Text • 2B • Updated • 5.29k • 59 -
AIDC-AI/Ovis2-4B
Image-Text-to-Text • 5B • Updated • 69.1k • 62 -
AIDC-AI/Ovis2-8B
Image-Text-to-Text • 9B • Updated • 37.6k • 75 -
AIDC-AI/Ovis2-16B
Image-Text-to-Text • 16B • Updated • 368 • 101 -
AIDC-AI/Ovis2-34B
Image-Text-to-Text • 35B • Updated • 1.01k • 151 -
7
Ovis2 34B GPTQ Int4
📚Stays powerful, with much lighter VRAM usage
-
AIDC-AI/Ovis2-34B-GPTQ-Int4
Image-Text-to-Text • 8B • Updated • 2.9k • 8 -
AIDC-AI/Ovis2-34B-GPTQ-Int8
Image-Text-to-Text • 12B • Updated • 48 • 2 -
AIDC-AI/Ovis2-16B-GPTQ-Int4
Image-Text-to-Text • 5B • Updated • 171 • 5 -
AIDC-AI/Ovis2-8B-GPTQ-Int4
Image-Text-to-Text • 3B • Updated • 1.58k • 3 -
AIDC-AI/Ovis2-4B-GPTQ-Int4
Image-Text-to-Text • 2B • Updated • 3.65k • 3 -
AIDC-AI/Ovis2-2B-GPTQ-Int4
Image-Text-to-Text • 1B • Updated • 47 • 2