Base44 Superagents-AI agent that does it all
Mini toolsJina-VLM
By Jina AI
Jina-VLM is Jina AI’s 2.4B-parameter small multilingual VLM that couples a SigLIP2 vision encoder with a Qwen3 language model via an attention-pooling connector. It processes arbitrary-resolution images efficiently and reaches state-of-the-art performance on multilingual VQA among open 2B-scale models, while maintaining solid text-only abilities and being offered through Jina’s APIs and cloud deployments for production use.
New
Text
Gen 4
Overview
Jina-VLM is a 2.4B-parameter small multilingual vision-language model that links a SigLIP2 vision encoder with a Qwen3 backbone to deliver strong multilingual visual question answering on images.
About Jina AI
Jina AI is a company that specializes in AI technology with a focus on multimodal AI, offering open-source technology and innovative solutions.
View Company ProfileTools using Jina-VLM
No tools found for this model yet.
Last updated: February 25, 2026
