Introducing Mistral Large 4: Le chonk
Mistral previewed Mistral Large 4, a 1-trillion-parameter model with 49 billion active parameters.
Mistral released a preview of Mistral Large 4, a 1 trillion parameter model with 49 billion active parameters. It was trained on Mistral's cluster of 3,800 NVIDIA Grace Blackwell GPUs and is available through the Mistral API, with open weights promised by the end of the month. The API supports only two reasoning levels, "none" and "high". On Artificial Analysis it scores 38, just behind DeepSeek 4.1 Flash, a 552B model.
- Mistral Large 4 has 1 trillion parameters and 49 billion active.
- API preview is available; open weights are promised this month.
- Training used 3,800 NVIDIA Grace Blackwell GPUs.
- Artificial Analysis score is 38, just behind DeepSeek 4.1 Flash.
- Only "none" and "high" reasoning levels are supported.
Introducing Mistral Large 4: Le chonk Mistral are back in the game. Today they're releasing a preview of Mistral Large 4, a 1 trillion parameter, 49 billion active parameter model trained on their own cluster of 3,800 NVIDIA Grace Blackwell GPUs. The preview is available via their API. They promise to release the open weights model at the "end of this month". The model only supports two reasoning levels - "none" and "high" - via the Mistral API. Here are both pelicans - the "high" one looks better, though surprisingly it only used 2,717 output tokens compared to "none" which used 3,275: On Artificial Analysis it scores 38 , just behind DeepSeek 4.1 Flash, which is a 552B model. It's a huge…
This source does not provide full text. Read it at simonwillison.net.