@Modular: Our kernel team has been deep in MiniMax M3 all week. The 1M-token context and native multimodality make it a hard mode…
Summary
Modular's kernel team is optimizing serving for MiniMax M3's 1M-token context and native multimodality, with open weights dropping soon for immediate deployment on Modular.
View Cached Full Text
Cached at: 06/10/26, 12:20 AM
Our kernel team has been deep in MiniMax M3 all week. The 1M-token context and native multimodality make it a hard model to serve well, which is exactly the kind of problem we like!
When the open weights drop in the next few days, you’ll be able to run it on Modular right away.
Stay tuned for @MiniMax_AI x Modular.
Similar Articles
MiniMax promises M3 weights after 1M-context model launch (2 minute read)
MiniMax released M3, a model with a 1M-token context window and native multimodal input, via API. The company promises open-weight release and a technical report within 10 days.
MiniMax M3 (2 minute read)
MiniMax introduces M3, the first open-weights model to combine coding, agentic, and multimodal capabilities with up to 1M context via sparse attention.
@PrajwalTomar_: Everyone's sleeping on MiniMax. Again. They just shipped M3. The first open-weights model to combine frontier coding, 1…
MiniMax released M3, an open-weights model combining frontier coding, 1M context, and native multimodality, offering comparable performance to Opus at a fraction of the cost.
MiniMax teases upcoming M3 model with new sparse attention mechanism and 15.6X long-context response speed boost (12 minute read)
MiniMax has released a detailed technical report on its M2 series and teased the upcoming M3 model, which uses a novel sparse attention mechanism to achieve up to 15.6× faster decoding at million-token contexts.
MiniMaxAI/MiniMax-M3
MiniMax releases M3, a native multimodal model with 1M context and ~428B parameters, using MiniMax Sparse Attention (MSA) for efficient long-context processing, achieving frontier-level coding and agentic performance.