@ClementDelangue: Le fat chaton! https://huggingface.co/mistralai/Mistral-Large-4.0-1T05-A52B…
Summary
Clement Delangue teases the upcoming Mistral Large 4 ("Le Chonk"), a 1-trillion-parameter natively multimodal model with 49B active parameters per token (52B including embeddings/output layers), with open weights expected on Hugging Face at the end of the month.
View Cached Full Text
Cached at: 10/06/26, 03:48 PM
Le fat chaton! https://huggingface.co/mistralai/Mistral-Large-4.0-1T05-A52B…
mistralai/Mistral-Large-4.0-1T05-A52B · Upcoming release · Hugging Face
Source: https://huggingface.co/mistralai/Mistral-Large-4.0-1T05-A52B
https://huggingface.co/mistralai/Mistral-Large-4.0-1T05-A52B#mistral-large-4—le-chonkMistral Large 4 - Le Chonk
Mistral Large 4 is a 1 trillion-parameter natively multimodal model with 49 billion active parameters per token (52 billion including embeddings and output layers). Open weights drop at the end of the month.
Waiting for the release237
Expected releaseOctober 31, 2026## Planned artifacts1
mistralai/Mistral-Large-4.0-1T05-A52B
Latest from mistralai
mistralai/Shieldstral-1.0-3Bmistralai/Leanstral-1.5-119B-A6Bmistralai/Mistral-Medium-3.5-128B-EAGLE
Similar Articles
LE CHATON FAT IS REAL
Mistral AI introduces Mistral Large 4 (Le Chonk), a natively multimodal 1T-parameter model with 49B active parameters, claiming best-in-class open weights performance from the US or Europe, state-of-the-art results on critical workloads like cyber defense and finance, and end-to-end European sovereignty, available via API with open weights releasing end of October.
Introducing Mistral Large 4: Le chonk
Mistral has released a preview of Mistral Large 4, a 1-trillion-parameter (49B active) model trained on 3,800 NVIDIA Grace Blackwell GPUs, with open weights promised later this month; it scores 38 on Artificial Analysis, a huge leap over Mistral Large 3.
Mistral Large 4
Mistral releases Mistral Large 4 ('Le Chonk'), a natively multimodal 1T-parameter model with 49B active parameters, claiming best open-weights performance aggregated benchmarks and state-of-the-art results on workloads like cyber defense, manufacturing, and finance. It is developed and deployable entirely in Europe, available via API now with open weights expected end of October.
Introducing Mistral Large 4
Mistral AI 发布了其最大模型 Mistral Large 4（代号 le Chonk）：一个 1 万亿参数、490 亿激活参数的原生多模态开源权重模型，公开预览 API 已上线，完整权重将于月底开源，强调欧洲自主基础设施与 AI 主权。
Mistral Large 4
Mistral AI announced Mistral Large 4, a state-of-the-art open-weight, general-purpose multimodal model with a granular MoE architecture featuring 49B active parameters, 1.05T total parameters, a 1.6B vision encoder, and a 1M token context window.