Title: Vision LLMs: text and image input %E2%80%94 LLM EU Canonical: https://llmeu.com/it/use/vision/ Markdown mirror: https://llmeu.com/it/use/vision.md Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json # Vision LLMs: text and image input Models that accept images as well as text. 68 models %C2%B7 [Open in the catalogue filter](/it/models/?modality=vision) - [Blip2 Flan T5 Xl](/it/models/blip2-flan-t5-xl/) %E2%80%94 Salesforce %C2%B7 3.9B %C2%B7 mit - [Blip2 Opt 2.7B](/it/models/blip2-opt-2-7b/) %E2%80%94 Salesforce %C2%B7 3.7B %C2%B7 mit - [Command A+ (05-2026)](/it/models/command-a-plus-05-2026/) %E2%80%94 Cohere %C2%B7 218.75B %C2%B7 128K %C2%B7 apache-2.0 - [DeepSeek OCR](/it/models/deepseek-ocr/) %E2%80%94 DeepSeek %C2%B7 3.3B %C2%B7 mit - [DeepSeek OCR 2](/it/models/deepseek-ocr-2/) %E2%80%94 DeepSeek %C2%B7 3.4B %C2%B7 apache-2.0 - [DeepSeek V4.1 Flash](/it/models/deepseek-v4-1-flash/) %E2%80%94 DeepSeek %C2%B7 763.2B %C2%B7 mit - [Diffusiongemma 26B A4B It](/it/models/diffusiongemma-26b-a4b-it/) %E2%80%94 Google DeepMind %C2%B7 25.8B %C2%B7 apache-2.0 - [ERNIE 4.5 VL 28B-A3B](/it/models/ernie-4-5-vl-28b-a3b/) %E2%80%94 Baidu %C2%B7 29.4B %C2%B7 apache-2.0 - [Florence 2 Base Ft](/it/models/florence-2-base-ft/) %E2%80%94 Microsoft %C2%B7 0.2B %C2%B7 mit - [Florence 2 Large Ft](/it/models/florence-2-large-ft/) %E2%80%94 Microsoft %C2%B7 0.8B %C2%B7 mit - [Gemma 3 12B It](/it/models/gemma-3-12b-it/) %E2%80%94 Google DeepMind %C2%B7 12.2B %C2%B7 gemma - [Gemma 3 27B It](/it/models/gemma-3-27b-it/) %E2%80%94 Google DeepMind %C2%B7 27.4B %C2%B7 gemma - [Gemma 3 4B It](/it/models/gemma-3-4b-it/) %E2%80%94 Google DeepMind %C2%B7 4.3B %C2%B7 gemma - [Gemma 4 12B It](/it/models/gemma-4-12b-it/) %E2%80%94 Google DeepMind %C2%B7 12B %C2%B7 apache-2.0 - [Gemma 4 26B A4B IT](/it/models/gemma-4-26b-a4b-it/) %E2%80%94 Google DeepMind %C2%B7 25.81B %C2%B7 256K %C2%B7 apache-2.0 - [Gemma 4 31B](/it/models/gemma-4-31b/) %E2%80%94 Google DeepMind %C2%B7 32.7B %C2%B7 apache-2.0 - [Gemma 4 31B IT](/it/models/gemma-4-31b-it/) %E2%80%94 Google DeepMind %C2%B7 31.27B %C2%B7 256K %C2%B7 apache-2.0 - [Gemma 4 E2B It](/it/models/gemma-4-e2b-it/) %E2%80%94 Google DeepMind %C2%B7 5.1B %C2%B7 apache-2.0 - [Gemma 4 E4B IT](/it/models/gemma-4-e4b-it/) %E2%80%94 Google DeepMind %C2%B7 8B %C2%B7 128K %C2%B7 apache-2.0 - [GLM 4.1V 9B Thinking](/it/models/glm-4-1v-9b-thinking/) %E2%80%94 Z.ai (Zhipu AI) %C2%B7 10.3B %C2%B7 mit - [GLM 4.5V](/it/models/glm-4-5v/) %E2%80%94 Z.ai (Zhipu AI) %C2%B7 107.7B %C2%B7 mit - [GLM 4.6V Flash](/it/models/glm-4-6v-flash/) %E2%80%94 Z.ai (Zhipu AI) %C2%B7 10.3B %C2%B7 mit - [GLM 5.3 Flash](/it/models/glm-5-3-flash/) %E2%80%94 Z.ai (Zhipu AI) %C2%B7 321.3B %C2%B7 mit - [GLM-OCR](/it/models/glm-ocr/) %E2%80%94 Z.ai (Zhipu AI) %C2%B7 1.33B %C2%B7 128K %C2%B7 mit - [Granite 4.0 3B Vision](/it/models/granite-4-0-3b-vision/) %E2%80%94 IBM %C2%B7 4B %C2%B7 apache-2.0 - [Granite Docling 258M](/it/models/granite-docling-258m/) %E2%80%94 IBM %C2%B7 0.3B %C2%B7 apache-2.0 - [Granite Vision 4.1 4B](/it/models/granite-vision-4-1-4b/) %E2%80%94 IBM %C2%B7 4B %C2%B7 apache-2.0 - [HunyuanOCR](/it/models/hunyuanocr/) %E2%80%94 Tencent %C2%B7 1.1B %C2%B7 other - [Instructblip Flan T5 Xl](/it/models/instructblip-flan-t5-xl/) %E2%80%94 Salesforce %C2%B7 4B %C2%B7 mit - [Instructblip Vicuna 7B](/it/models/instructblip-vicuna-7b/) %E2%80%94 Salesforce %C2%B7 7.9B %C2%B7 other - [Intern-S1](/it/models/intern-s1/) %E2%80%94 Shanghai AI Laboratory %C2%B7 240.7B %C2%B7 apache-2.0 - [Intern-S1 Mini](/it/models/intern-s1-mini/) %E2%80%94 Shanghai AI Laboratory %C2%B7 8.5B %C2%B7 apache-2.0 - [Kimi K2.5](/it/models/kimi-k2-5/) %E2%80%94 Moonshot AI %C2%B7 1026.9B %C2%B7 other - [Kimi K2.6](/it/models/kimi-k2-6/) %E2%80%94 Moonshot AI %C2%B7 1026.9B %C2%B7 other - [Kimi K2.7 Code](/it/models/kimi-k2-7-code/) %E2%80%94 Moonshot AI %C2%B7 1026.9B %C2%B7 other - [Kimi K3](/it/models/kimi-k3/) %E2%80%94 Moonshot AI %C2%B7 2779.9B %C2%B7 other - [Kimi VL A3B Instruct](/it/models/kimi-vl-a3b-instruct/) %E2%80%94 Moonshot AI %C2%B7 16.4B %C2%B7 mit - [Llama 3.2 11B Vision Instruct](/it/models/llama-3-2-11b-vision-instruct/) %E2%80%94 Meta %C2%B7 10.7B %C2%B7 llama3.2 - [Llama 4 Maverick 17B-128E Instruct](/it/models/llama-4-maverick-17b-128e-instruct/) %E2%80%94 Meta %C2%B7 401.58B %C2%B7 1024K %C2%B7 other - [Llama 4 Scout 17B-16E Instruct](/it/models/llama-4-scout-17b-16e-instruct/) %E2%80%94 Meta %C2%B7 108.64B %C2%B7 10240K %C2%B7 other - [Llama Guard 4 12B](/it/models/llama-guard-4-12b/) %E2%80%94 Meta %C2%B7 12B %C2%B7 other - [Magistral Small 1.2](/it/models/magistral-small-1-2/) %E2%80%94 Mistral AI %C2%B7 24.01B %C2%B7 128K %C2%B7 apache-2.0 - [Medgemma 4B It](/it/models/medgemma-4b-it/) %E2%80%94 Google DeepMind %C2%B7 4.3B %C2%B7 other - [MiniMax M3](/it/models/minimax-m3/) %E2%80%94 MiniMax %C2%B7 427B %C2%B7 other - [Ministral 3 8B](/it/models/ministral-3-8b/) %E2%80%94 Mistral AI %C2%B7 8.92B %C2%B7 256K %C2%B7 apache-2.0 - [Mistral Large 3 (675B)](/it/models/mistral-large-3-675b/) %E2%80%94 Mistral AI %C2%B7 675B %C2%B7 256K %C2%B7 apache-2.0 - [Mistral Small 4 (119B-A6B)](/it/models/mistral-small-4-119b-a6b/) %E2%80%94 Mistral AI %C2%B7 119.4B %C2%B7 256K %C2%B7 apache-2.0 - [Molmo 7B D 0924](/it/models/molmo-7b-d-0924/) %E2%80%94 Allen Institute for AI (Ai2) %C2%B7 8B %C2%B7 apache-2.0 - [Molmo2 4B](/it/models/molmo2-4b/) %E2%80%94 Allen Institute for AI (Ai2) %C2%B7 4.9B %C2%B7 apache-2.0 - [Molmo2 8B](/it/models/molmo2-8b/) %E2%80%94 Allen Institute for AI (Ai2) %C2%B7 8.7B %C2%B7 apache-2.0 - [North Micro Vision Instruct](/it/models/north-micro-vision-instruct/) %E2%80%94 Cohere %C2%B7 2.5B %C2%B7 apache-2.0 - [NVIDIA Cosmos Reason2 2B](/it/models/cosmos-reason2-2b/) %E2%80%94 NVIDIA %C2%B7 2.4B %C2%B7 other - [NVIDIA Nemotron 3 Nano Omni 30B-A3B Reasoning](/it/models/nemotron-3-nano-omni-30b-a3b-reasoning/) %E2%80%94 NVIDIA %C2%B7 33B %C2%B7 other - [OlmOCR 2 7B 1025](/it/models/olmocr-2-7b-1025/) %E2%80%94 Allen Institute for AI (Ai2) %C2%B7 8.3B %C2%B7 apache-2.0 - [OlmOCR 7B 0225 Preview](/it/models/olmocr-7b-0225-preview/) %E2%80%94 Allen Institute for AI (Ai2) %C2%B7 8.3B %C2%B7 apache-2.0 - [Phi 3.5 Vision Instruct](/it/models/phi-3-5-vision-instruct/) %E2%80%94 Microsoft %C2%B7 4.1B %C2%B7 mit - [Phi-4-multimodal-instruct](/it/models/phi-4-multimodal-instruct/) %E2%80%94 Microsoft %C2%B7 5.57B %C2%B7 128K %C2%B7 mit - [Pixtral 12B](/it/models/pixtral-12b/) %E2%80%94 Mistral AI %C2%B7 12B %C2%B7 128K %C2%B7 apache-2.0 - [Qianfan OCR](/it/models/qianfan-ocr/) %E2%80%94 Baidu %C2%B7 4.7B %C2%B7 apache-2.0 - [Qwen2.5 VL 7B Instruct](/it/models/qwen2-5-vl-7b-instruct/) %E2%80%94 Alibaba Qwen %C2%B7 8.3B %C2%B7 apache-2.0 - [Qwen3 VL 4B Instruct](/it/models/qwen3-vl-4b-instruct/) %E2%80%94 Alibaba Qwen %C2%B7 4.4B %C2%B7 apache-2.0 - [Qwen3-VL-8B-Instruct](/it/models/qwen3-vl-8b-instruct/) %E2%80%94 Alibaba Qwen %C2%B7 8.77B %C2%B7 256K %C2%B7 apache-2.0 - [Qwen3.5 2B](/it/models/qwen3-5-2b/) %E2%80%94 Alibaba Qwen %C2%B7 2.3B %C2%B7 apache-2.0 - [Qwen3.5 4B](/it/models/qwen3-5-4b/) %E2%80%94 Alibaba Qwen %C2%B7 4.7B %C2%B7 apache-2.0 - [Qwen3.5 9B](/it/models/qwen3-5-9b/) %E2%80%94 Alibaba Qwen %C2%B7 9.7B %C2%B7 apache-2.0 - [Qwen3.6 35B A3B](/it/models/qwen3-6-35b-a3b/) %E2%80%94 Alibaba Qwen %C2%B7 36B %C2%B7 apache-2.0 - [Qwen3.8-27B](/it/models/qwen3-8-27b/) %E2%80%94 Alibaba Qwen %C2%B7 27.78B %C2%B7 256K %C2%B7 apache-2.0 - [Unlimited OCR](/it/models/unlimited-ocr/) %E2%80%94 Baidu %C2%B7 3.3B %C2%B7 mit [open-weights](/it/use/open-weights/) %C2%B7[eu-builders](/it/use/eu-builders/) %C2%B7[german](/it/use/german/) %C2%B7[french](/it/use/french/) %C2%B7[long-context](/it/use/long-context/) %C2%B7[coding](/it/use/coding/) %C2%B7[rag](/it/use/rag/) %C2%B7[audio](/it/use/audio/) %C2%B7[apache-2](/it/use/apache-2/) %C2%B7[self-hostable](/it/use/self-hostable/) %C2%B7[catalogue-only](/it/use/catalogue-only/)