MiniMax-M3 is an open-source multimodal AI foundation model supporting up to 1 million context tokens. It can be run locally via CLI or Docker, enabling advanced inference for text, image, and other modalities. Designed for AI researchers and developers seeking customizable, large-context models.
In the Other models space, MiniMax M3 takes a focused approach. Enabling developers to run large-context multimodal AI models locally for advanced inference tasks. MiniMax M3 is an open-source project aimed at AI researchers and developers. MiniMax M3 is open source under the Open Source license. It runs on the command line, and it can be self-hosted.
MiniMaxAI builds and maintains MiniMax M3, and it first shipped in 2026. Among its 5 catalogued features are multimodal input, large context window, and open weights.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do