Checked fact 315830 Oct 2026Models and releases

The model card lists a 1M-token context length and a granular Mixture-of-Experts design with 128 routed experts, 4 active per token, and 1 shared expert.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

~1T total / ~52B active parameters: granular Mixture-of-Experts with 128 routed experts (4 active per token) and 1 shared expert. 1M context length, for long-context workloads.

What the source said when we opened it, on 30 Oct 2026.

The source

Mistral-Large-4-1T-A52B model card
Mistral AI (Hugging Face)

Open the source archived copy

Checked

Checked by the notis newsroom on 30 Oct 2026, against the source above.

In the story

Mistral releases Large 4 weights, but paid hosting needs a separate licence 30 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The model card lists a 1M-token context length and a granular Mixture-of-Experts design with 128 routed experts, 4 active per token, and 1 shared expert.” ai notis, checked 30 Oct 2026. Source: Mistral-Large-4-1T-A52B model card (Mistral AI (Hugging Face)). https://ainotis.com/c/3158

As a reference (APA style)

ai notis. (2026, October 30). The model card lists a 1M-token context length and a granular Mixture-of-Experts design with 128 routed experts, 4 active per token, and 1 shared expert [Checked claim 3158]. ai notis. https://ainotis.com/c/3158

Anyone may quote this address. It does not change; if we correct the story, this page says so.