Woofun AI reports that MiniMax is developing a 27 trillion parameter large language model, internally codenamed M3 Pro, with plans to open-source it as early as the third quarter. The final release name remains undetermined.

The new model is approximately 6.3 times larger than MiniMax's current flagship M3, which has 428 billion parameters. If released as planned, it will surpass existing trillion-parameter open-weight models to become the world's largest open-source large model in terms of parameters.