Ir para o conteúdo
Atlas de IA

MiniMax-M

Um modelo de raciocínio de pesos abertos com atenção híbrida e contexto de um milhão de tokens

MiniMax Modelo Pesos abertos
entradaTextoTexto

O texto completo é apresentado em inglês; o título e o resumo estão traduzidos.

O QUE É

MiniMax-M1 is an open-weight reasoning model MiniMax released in June 2025. MiniMax was founded in Shanghai in 2021 by Yan Junjie and others. M1 uses a hybrid attention design that combines standard full-attention layers with linear-attention layers to cut the compute cost of long-sequence reasoning, and its stated context window reaches the million-token range. With 456B total parameters activating about 46B per token, it is a large-scale MoE reasoning model whose weights are released under an open licence. The company also runs generation product lines such as Hailuo.

Por que vale a pena lembrar

It mixes linear and full attention and pushes context to a million tokens to cut the cost of long-sequence reasoning; among the larger open-weight reasoning models, it is a concrete landing of the open-weight camp on the reasoning track.

Especificações-chave

Parameters
456B (MoE, ~46B active)
Context window
1M tokens
Architecture
Hybrid linear and full attention
Open weights
Yes

Capacidades

Conceitos relacionados

Produtos semelhantes