This is an NVIDIA-optimized FP4 quantized version of the MiniMax-M3 multimodal foundation model. It supports text, image, and video understanding along with advanced tool-calling features. The quantization enables faster and more memory-efficient inference on NVIDIA hardware while preserving model capabilities.
MiniMax M3 sits in PulseGate's Multimodal & vision category. It focuses on running large multimodal models efficiently with reduced memory and compute requirements. It is built as an open-source project for developers. The project is open source (Apache-2.0). MiniMax M3 is available on the web and API.
It is developed by NVIDIA (United States), and it first shipped in 2024. The project is developed in the open on GitHub with 3.3k stars and 356 commits in the last 90 days. Among its 3 catalogued features are Multimodal Processing, Tool Calling, and FP4 Quantization.
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