MiniMax releases M3 native multimodal model with 1M-token context
MiniMax published MiniMax-M3 on Hugging Face, describing it as a native multimodal model with a 1M-token context, approximately 428B total parameters and 23B activated parameters. The model card says mixed-modality training combines text, image and video semantics, while MiniMax Sparse Attention targets more efficient million-token inference. MiniMax also claims 9× prefill and 15× decode speedups over M2 at 1M context, but these performance and efficiency figures have not been independently verified.
MiniMax-M3 combines native multimodality, million-token context and downloadable deployment support, making it a notable new model for long-context multimodal and agentic workloads.
MiniMaxAI/MiniMax-M3 Image-Text-to-Text • 427B • Updated 5 days ago • 200k • • 1.6k
pipeline_tag: image-text-to-text license: other license_name: minimax-community license_link: LICENSE library_name: transformers tags:
- multimodal
- moe
- agent
- coding
- video
