MiMo-V2.6-Pro is the flagship foundation model from Xiaomi, built at a scale of over 1T parameters for the most demanding workloads. It has a 1M-token context window and native multimodal support. It is optimized for agentic workflows and performs at a high level across coding, visual, general, and research scenarios, including complex, long-horizon tasks across many agent harnesses.
MiMo-V2.6-Flash is an open-source foundation model from Xiaomi. It uses a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, plus a hybrid attention mechanism for better compute efficiency. It has a 1M-token context window and native multimodal support, and is tuned for agentic workflows in coding, visual, general, and research scenarios, including long-horizon tasks with different agent harnesses.