Image + textDocuments and OCR

MiniCPM-V

Compact vision models that run even on a phone or laptop. Good at reading text in photos and understanding video; version 4.6 is only 1.3B.

Developer
OpenBMB (ModelBest and Tsinghua University), China
First release
Jan 2024
Latest release
May 2026
Sizes
1.3B – 8B
License
Commercial use allowedApache 2.0 (early versions had their own MiniCPM license requiring registration for commercial use)
Russian
Not stated
Ready-made builds
GGUF, AWQ, GPTQ, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Documents and accounting, Retail and marketplaces, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • On-device text recognition in photos
  • Processing receipts and documents without sending them to the cloud
  • Describing photos and video
  • A built-in assistant for a mobile app

Where it is used

Mobile appsRetailField services

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
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. MiniCPM-V 4.6 и 4.6-Thinking
  2. MiniCPM-V 4.5
  3. MiniCPM-V 4.0
  4. MiniCPM-V 2.6
  5. MiniCPM-Llama3-V 2.5
  6. MiniCPM-V 2.0
  7. MiniCPM-V

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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 MiniCPM-V be used in a commercial project?

Yes. License: Apache 2.0 (early versions had their own MiniCPM license requiring registration for commercial use). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does MiniCPM-V 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 MiniCPM-V support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download MiniCPM-V and what does it cost?

The MiniCPM-V 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 + textQwen-VLAlibaba (Qwen team) · ChinaCommercial use allowed

One of the strongest open vision models: reads documents, tables, charts and video, and works with user interfaces. Since Qwen3.5, vision is built directly into the main Qwen model.

DetailsImage + 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.

DetailsVoice assistantsMiniCPM-oOpenBMB (ModelBest, Tsinghua University) · ChinaCommercial use allowed

A small model that sees, hears and replies by voice in real time, and can clone a voice. Voice dialogue in English and Chinese, text in 30+ languages.

Details

Source: huggingface.co/openbmb/MiniCPM-V-4.6. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.