Image + text

IDEFICS

Open vision models from Hugging Face that reproduced the closed Flamingo. Idefics3 became the basis for the compact SmolVLM line.

The last open version came out in Aug 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Hugging Face, France / USA
First release
Jul 2023
Latest release
Aug 2024
Sizes
8B – 80B
License
Commercial use allowedIdefics2 and Idefics3: Apache 2.0; the first IDEFICS on LLaMA: research only
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Science and research, Media and production
Deploy on your server Hugging Face

What it does

  • Answering questions about images
  • Analysing documents and screenshots
  • A base for fine-tuning

Where it is used

Research teamsE-commerce

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Idefics3-8B-Llama3
  2. Idefics2-8B
  3. IDEFICS 9B / 80B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can IDEFICS be used in a commercial project?

Yes. License: Idefics2 and Idefics3: Apache 2.0; the first IDEFICS on LLaMA: research only. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does IDEFICS need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does IDEFICS support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download IDEFICS and what does it cost?

The IDEFICS weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Image + textSmolVLMHugging Face · France / USACommercial use allowed

The smallest vision models from Hugging Face, starting at 256M; they run in a browser and on a phone. SmolVLM2 also understands video.

DetailsImage + textLLaVALLaVA / LMMs-Lab (researchers from the USA and China) · USA / ChinaCommercial use allowed

The open project that started the trend for image-plus-text models. The OneVision line understands photos, documents and video; training data and recipes are open.

DetailsImage + textMolmoAi2 (Allen Institute for AI) · USACommercial use allowed

Fully open vision models from Ai2 (weights and data). They can point to a spot in an image and count objects; Molmo2 understands video, MolmoWeb controls a browser.

Details

Source: huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.