Vision and multimodal AI

Models that read images, documents and video as well as text. 27 listed, most used first.

Qwen3.8-Flash-NextAlibaba (Qwen) · vision and multimodal model
Aug 24, 2026released
Florence-2Microsoft · vision and multimodal model
Jun 15, 2024released
Unlimited-OCRBaidu · vision and multimodal model
Jun 19, 2026released
moondream2Vikhyatk · vision and multimodal model
Mar 4, 2024released
DeepSeek-OCRDeepSeek · vision and multimodal model
Oct 17, 2025released
Chandra-OCR-2Datalab To · vision and multimodal model
Mar 16, 2026released
Surya-OCR-2Datalab To · vision and multimodal model
May 14, 2026released
HunyuanOCRTencent · vision and multimodal model
Nov 18, 2025released
Llava-1.5Llava Hf · vision and multimodal model
Dec 5, 2023released
Vllm-TranslategemmaInfomaniak AI · vision and multimodal model
Jan 26, 2026released
diffusiongemmaGoogle · vision and multimodal model
Jun 9, 2026released
Qwen3-OmniAlibaba (Qwen) · vision and multimodal model
Sep 20, 2025released
Gemma-4-AssistantGoogle · vision and multimodal model
Apr 23, 2026released
Qwen3-Omni-ThinkingAlibaba (Qwen) · vision and multimodal model
Sep 15, 2025released
Qwen2.5-OmniAlibaba (Qwen) · vision and multimodal model
Mar 22, 2025released
Gemma-4-AssistantGoogle · vision and multimodal model
Apr 23, 2026released
MiniCPM-o-4 5OpenBMB · vision and multimodal model
Feb 3, 2026released
Nemotron-3-Nano-Omni-ReasoningNVIDIA · vision and multimodal model
Apr 20, 2026released
MiniCPM-o-2 6OpenBMB · vision and multimodal model
Jan 12, 2025released
Janus-ProDeepSeek · vision and multimodal model
Jan 26, 2025released
Gemma-4-AssistantGoogle · vision and multimodal model
Apr 23, 2026released
Qwen3-Omni-CaptionerAlibaba (Qwen) · vision and multimodal model
Sep 15, 2025released
Nemotron-3.5-ParseNVIDIA · vision and multimodal model
Sep 3, 2026released
Ming-flash-omni-2.0InclusionAI · vision and multimodal model
Feb 10, 2026released
SenseNova-U1.5-MoTSensenova · vision and multimodal model
Aug 19, 2026released
WeVisOne-VLTencent · vision and multimodal model
Oct 22, 2026released
Unlimited-OCR-2Baidu · vision and multimodal model
Oct 26, 2026released