Mistral Large 4

In non-nerd speak

Who makes it: Mistral AI. The files come from the maker's own Hugging Face account.

License: Mistral Ecosystem Open-Weight License. Mistral's own version of the MIT license. You can use, change, and share it, even to make money. Selling access to the model itself as a service needs a paid deal.

Business use: Yes for most businesses. If you run a business that lets other people use the model through an API or hosted service, you need a separate paid license from Mistral first. Using it inside your own company, or inside your own app's features, is fine.

Training data: We have not found a full public data release. Not yet checked in depth.

Will it say no?

Not sure yet. Mistral's card says it turns down harmful security requests. It does not say how often it says no to other things. So we won't guess.

This comes from what the maker wrote, checked Oct 29, 2026. We have not run our own tests yet. It sits next to the trust score and does not change it. How we pick these labels.

Will it run on my computer?

Not for home computers. This one needs server-class hardware, or Mistral AI's own suggested setup, with hundreds of GB of memory. Most people should use it through a hosted service instead. This model uses a mix of experts. Only part of it works on each word, so it runs faster than its size suggests.

Not sure? Use our pick-by-computer guide.

How to run it in LM Studio

1. Get LM Studio from lmstudio.ai and open it.
2. Open the Discover tab. Search for ggml-org/Mistral-Large-4-1T-A52B-GGUF.
3. Pick a file that ends in Q4_K_M. It is the best mix of size and quality for most people.
4. Click Download. When it is done, open a new chat and load the model.

The files are GGUF builds that LM Studio can load. We checked that this repo exists on Oct 29, 2026. Full LM Studio guide.

How to use it with Hermes

Does it fit? Yes. Its memory window is big enough for Hermes.

1. Load the model in LM Studio. Set the context length to at least 64000.
2. In LM Studio, open the Developer tab and start the server.
3. In a terminal, run hermes model. Choose LM Studio and press Enter to keep http://localhost:1234/v1.
4. Pick this model from the list. Then run hermes to start.

Steps based on the Hermes docs. Full Hermes guide.

Common questions

Is Mistral Large 4 truly open source?

No, open weights with custom rules. Mistral's own version of the MIT license. You can use, change, and share it, even to make money. Selling access to the model itself as a service needs a paid deal.

Can I use Mistral Large 4 for my business?

Yes for most businesses. If you run a business that lets other people use the model through an API or hosted service, you need a separate paid license from Mistral first. Using it inside your own company, or inside your own app's features, is fine.

Do I need to sign up to download Mistral Large 4?

No. Download without an account.

How much memory does Mistral Large 4 need?

Our estimate is about 764 GB of RAM for a 4-bit file of about 634.8 GB. This is a rough guide, not a test.

Similar models to compare

Same maker first, then models that need about the same memory.

Where Mistral Large 4 shows up

• What its license means

Change history

• Oct 29, 2026 New model Mistral Large 4: Added Mistral AI's Mistral Large 4. A huge model for coding, agents, and reading images, with about 1 trillion parameters. Mistral Ecosystem Open-Weight License; business use is fine unless you sell model access as a service. No sign-up needed. Not a home-computer model.

All changes on the site

Sources we checked

If the maker's page and this page disagree, trust the maker. Tell us what we got wrong.