Text

MiniCPM

Compact text models that run directly on a device: laptop, phone or mini PC. The 1B and 2B MiniCPM5 models focus on tool calling and long context.

Developer
OpenBMB (ModelBest and Tsinghua University), China
First release
Feb 2024
Latest release
Sep 2026
Sizes
0.5B – 8B
License
Commercial use allowedApache 2.0 (the first MiniCPM-2B and MiniCPM 2.0 had their own MiniCPM license requiring registration for commercial use)
Russian
Not supported
Ready-made builds
AWQ, GPTQ, MLX (Apple)
Running
On your own serverAlso runs without a GPU
Industries
Customer support, Documents and accounting, Software development
Deploy on your server Hugging Face GitHub

What it does

  • A local chat assistant without the cloud
  • Data extraction and text classification
  • Tool calling and simple agents on low-end hardware

Where it is used

Customer supportDocument workflowEmbedded devices

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. MiniCPM5-2B
  2. MiniCPM5-1B
  3. MiniCPM4.1-8B
  4. MiniCPM4 (0.5B, 8B)
  5. MiniCPM3-4B
  6. MiniCPM 2.0 (1B, MoE 8x2B)
  7. MiniCPM-2B

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 be used in a commercial project?

Yes. License: Apache 2.0 (the first MiniCPM-2B and MiniCPM 2.0 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 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 support Russian?

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

Where can I download MiniCPM and what does it cost?

The MiniCPM 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

TextSmolLMHugging Face · USACommercial use allowed

Tiny open Hugging Face models for phones and laptops. SmolLM3 (3B) can reason and handle long context; the full training recipe is open.

DetailsTextLiquid LFMLiquid AI · USACommercial use with conditions

Models with a new architecture for on-device use: fast on a regular CPU and on phones. Versions for data extraction, RAG and tools, plus LFM2.5-VL for images and voice LFM2.5-Audio.

DetailsTextQwenAlibaba · ChinaCommercial use with conditions

A family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.

Details

Source: huggingface.co/openbmb/MiniCPM5-2B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.