TextImage + textVoice assistantsSpeech to text

MiMo

Xiaomi models for reasoning and agents: from the compact MiMo-7B to MiMo-V2.6-Pro with 1.02 trillion parameters. The larger versions understand text, images, video and audio, with a 1M token context. Languages: English and Chinese.

Developer
Xiaomi, China
First release
Apr 2025
Latest release
Sep 2026
Sizes
7B – 1,02T-A42B
License
Commercial use allowedMIT
Russian
Not supported
Ready-made builds
GGUF, MLX (Apple)
Running
On your own serverNeeds a GPU
Industries
Software development, Science and research, Finance
Deploy on your server Hugging Face GitHub

What it does

  • Logic and calculation tasks
  • Agents with tools
  • Help for developers

Where it is used

Software developmentAnalyticsElectronics manufacturing

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
fits

Versions

  1. MiMo-V2.6-Flash 309B-A15B / Pro 1,02T-A42B / Distill-Qwen-9B
  2. MiMo-V2.5 / V2.5-Pro / V2.5-ASR
  3. MiMo-V2-Flash
  4. MiMo-Audio-7B
  5. MiMo-VL-7B
  6. MiMo-7B

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 MiMo 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 MiMo 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 MiMo support Russian?

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

Where can I download MiMo and what does it cost?

The MiMo 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

TextStepStepFun · ChinaCommercial use allowed

StepFun MoE models built for fast, low-cost work: with 196 billion parameters, Step-3.5/3.7-Flash use about 11 billion per token. Compact Step3-VL-10B for images and voice Step-Audio 2 mini are available.

DetailsTextLongCatMeituan · ChinaCommercial use allowed

Models from Meituan, China's largest delivery service. LongCat-Flash adjusts compute to query complexity; LongCat-2.0 has 1.6 trillion parameters under MIT. Omni models (Flash-Omni, Next) and AudioDiT speech synthesis too.

DetailsTextDeepSeekDeepSeek · ChinaCommercial use allowed

DeepSeek's flagship line: from the first 7B/67B to V4-Pro with 1.6 trillion parameters. Closed-model quality under an open MIT license; V4-Flash-Vision-Exp and V4.1-Flash understand images, context up to 1M tokens.

Details

Source: huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.