mlx-h3 is a Python package that enables pure MLX-based inference for the MiniMax-H3 model, allowing text-to-video and text-to-audio generation directly on Apple Silicon devices. It leverages the MLX framework for efficient on-device performance without requiring cloud services. The project is open source and hosted on GitHub.
mlx-h3 is an AI & ML project. It focuses on running high-quality text-to-video and text-to-audio generative AI models locally on Apple Silicon hardware. mlx-h3 is an open-source project aimed at developers. mlx-h3 is open source under the Open Source license. It ships for the command line.
appautomaton builds and maintains mlx-h3, and it first shipped in 2026. Development happens publicly on GitHub with 2 commits in the last 90 days. Key capabilities include text-to-Video, text-to-Audio, and Apple Silicon Optimized.
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