Image + textComputer vision

Florence-2

A very small vision model: captions, object detection, segmentation and text reading from a single prompt. Runs even on a CPU.

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

Developer
Microsoft, USA
First release
Jun 2024
Latest release
Jun 2024
Sizes
0.23B – 0.77B
License
Commercial use allowedMIT
Russian
Not supported
Ready-made builds
MLX (Apple)
Running
On your own serverAlso runs without a GPU
Industries
Manufacturing and logistics, Media and production, Retail and marketplaces
Deploy on your server Hugging Face

What it does

  • Reading text in photos
  • Finding and highlighting objects
  • Automatic photo captions
  • Labelling data for training

Where it is used

ManufacturingRetailData labelling

Hardware requirements

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

Versions

  1. Florence-2 base / large

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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Florence-2 be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Florence-2 need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Florence-2 support Russian?

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

Where can I download Florence-2 and what does it cost?

The Florence-2 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.

Comparisons

Similar models

Image + textPaliGemmaGoogle · USACommercial use with conditions

Google's vision model built on Gemma, designed as a base for fine-tuning on a narrow task: captions, object detection, reading text.

DetailsImage + textMoondreamMoondream (M87 Labs) · USACommercial use with conditions

A small, fast vision model for product use cases: answering questions, finding and pointing to objects, captions. Moondream 3.1 is a 9B MoE with 2B active.

DetailsComputer visionGrounding DINO / Rex-OmniIDEA Research · ChinaCommercial use with conditions

Finds any objects in an image from a text description, without training on your data: "red box", "person without a hard hat". Rex-Omni is the new VLM-based generation.

Details

Source: huggingface.co/microsoft/Florence-2-large. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.