Service update · MiniMax
MiniMax releases M3.1 Flash weights for self-hosting
- Effective time
- Review updated
MiniMax has released M3.1 Flash weights on Hugging Face and ModelScope. The official model card lists approximately 428B total parameters, with 23B activated per token, text, image and video inputs, text output and a context window of up to 1M tokens. Usable context length and throughput depend on GPU memory and the serving configuration. The weights use the MiniMax Community license; review its terms before deployment. SGLang and vLLM support inference, and MiniMax confirms day-one fine-tuning support in NVIDIA NeMo.