Mistral 发布 Mistral Large 4:1T 参数多模态开源权重模型
Mistral 放出 1T 参数的多模态模型,激活只有 49B,API 现在就能用,10 月底开源权重,欧洲目前最能打的一个。
Mistral AI 发布 Mistral Large 4,总参数 1T、激活 49B,原生多模态,训练和推理均使用自家算力。
官方称其在聚合基准上是美国和欧洲最好的开源权重模型,并在网络防御、制造、金融等关键工作负载上达到 SOTA,视觉 grounding 超越闭源前沿模型。模型已在 Mistral Cloud 通过 API 开放使用,开源权重计划于 10 月底发布。
That one took some groundwork. Trained and served on our own compute, and RL shows no sign of saturation Mistral AI @MistralAI Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding. • Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure. • Available to all via API today. Working with cybersecurity partners privately. Open weights release end of October.
This report is categorized under AITOP's "Models" desk, focusing on Europe's AI governance and technology ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Mistral Large 4, Mistral AI, open-source models, multimodal.
Source attribution: curated from Arthur Mensch (@arthurmensch). Cross-source corroboration: 11 independent sources have covered this development (including Clement Delangue, Mistral AI, Julien Chaumond), confirming industry-wide signal strength.