TextImage + textCodeModeration and safety

Mistral

European models focused on speed. Mixtral was one of the first open mixture-of-experts models; there are versions for images (Pixtral, Medium 3.5), Lean proofs and moderation (Shieldstral).

Developer
Mistral AI, France
First release
Sep 2023
Latest release
Jul 2026
Sizes
3B – 675B
License
Commercial use with conditionsApache 2.0 (most versions, including Ministral 3, Pixtral 12B, Leanstral and Shieldstral); Mistral Medium 3.5: modified MIT, companies with large revenue need paid access
Russian
Supported
Ready-made builds
GGUF, AWQ, GPTQ, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Customer support, Documents and accounting, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Fast chat responses
  • Data extraction from text
  • Translation and multilingual work

Where it is used

Customer supportRequest processingEuropean projects

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. Leanstral 1.5 119B-A6B / Shieldstral-1.0-3B
  2. Mistral Medium 3.5 128B
  3. Mistral Small 4 / Leanstral
  4. Mistral Large 3 / Ministral 3 (3B, 8B, 14B)
  5. Magistral Small
  6. Mistral Small 3
  7. Pixtral 12B
  8. Mistral NeMo / Mathstral 7B
  9. Mixtral 8x7B
  10. Mistral 7B

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 Mistral be used in a commercial project?

With conditions. License: Apache 2.0 (most versions, including Ministral 3, Pixtral 12B, Leanstral and Shieldstral); Mistral Medium 3.5: modified MIT, companies with large revenue need paid access. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Mistral 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 Mistral support Russian?

Yes, Russian is listed on the model card.

Where can I download Mistral and what does it cost?

The Mistral 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

TextQwenAlibaba · 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.

DetailsTextLlamaMeta · USACommercial use with conditions

The models that started mass open source in AI. A huge ecosystem of fine-tuned versions and tools.

Details

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