← back to the directory
Model Inference & Serving

Idefics2

1Hugging 2Face's 3open 4multimodal 5chat 6model

the six Ws · specification

W1 Who

Hugging Face's M4 research team created Idefics2.

W2 What

An 8-billion-parameter open multimodal model for image-text dialogue and document understanding.

W3 Where

Hosted on Hugging Face under the HuggingFaceM4 organization.

W4 When

Idefics2 was released in April 2024, succeeding Idefics released in 2023.

W5 Why

It provided a fully open, reproducible alternative to Flamingo-style multimodal models with transparent training data.

W6 With

Runs on transformers, combining a Mistral-7B language model with a SigLIP vision encoder.

W7 Watch

Open-weight release by Hugging Face under Apache 2.0 license, with fully documented training data.

vision-languagemultimodalhugging-faceopen-source

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.