MiniMax M3 releases with 1M context, native multimodality and sparse attention
Original titleMiniMax M3: Frontier Coding, 1M Context, Native Multimodality — All in One Model
AISummary
MiniMax released M3, an open-weight model with a 1M-token context window, native image and video input, and desktop operation support.
The post credits a new sparse attention architecture, MSA, for long-context gains, reporting over 9x prefilling and over 15x decoding speedups and 59.0% on SWE-Bench Pro.
The API and MiniMax Code are available now, with the technical report and open weights promised within 10 days.
AIWhy it matters
The post pairs a new sparse attention design with benchmark figures and a 1M-token context window, letting readers judge the architecture's practical effect on long-context work.
Source: MiniMax Blog · minimax.io