Voice assistantsImage + text

MiniCPM-o

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.

Developer
OpenBMB (ModelBest, Tsinghua University), China
First release
Jan 2025
Latest release
Feb 2026
Sizes
8B – 9B
License
Commercial use allowedApache 2.0
Russian
Not supported
Ready-made builds
GGUF, AWQ, GPTQ, MLX (Apple)
Running
On your own serverNeeds a GPU
Industries
Retail and marketplaces, Manufacturing and logistics, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Voice assistant on your own server
  • Analyzing videos and documents
  • Voice answers about a camera image

Where it is used

Retail and serviceManufacturingProduct development

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-o 4.5
  2. MiniCPM-o 2.6

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 MiniCPM-o be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does MiniCPM-o need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 MiniCPM-o support Russian?

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

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

The MiniCPM-o 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

Voice assistantsQwen OmniAlibaba (Qwen) · ChinaCommercial use allowed

Models that understand text, images, audio and video and reply by voice in real time. Qwen3-Omni speaks 10 languages, including Russian.

DetailsImage + textMiniCPM-VOpenBMB (ModelBest and Tsinghua University) · ChinaCommercial use allowed

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.

DetailsVoice assistantsMoshi / HibikiKyutai · FranceCommercial use with conditions

A voice assistant that listens and speaks at the same time, with no delay for recognition and synthesis. Hibiki does simultaneous speech-to-speech translation between several European languages.

Details

Source: huggingface.co/openbmb/MiniCPM-o-4_5. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.