MiniMax-H3, the multimodal generation system that accepts text, images, audio, and video and produces clips of up to 15 seconds with audio, can now run on Apple Silicon. A community Python package, PipeNetwork/minimax-h3-mlx, ports the model to MLX.
Simon Willison tested the port on an M5 Max MacBook Pro. The model download is roughly 115GB. His video generation run took under 45 minutes, which puts the model in the realm of batch local work rather than interactive use.
What the MLX Port Actually Is
The package wraps MiniMax-H3 for MLX, Apple’s machine learning framework for Apple Silicon. That means the model runs on the unified memory of the M-series chips without a separate GPU.
The practical significance is straightforward. MiniMax-H3 was announced as a flagship multimodal system, and most local-run claims for models like this end up being theoretical. Here there is a working port with a documented test on real hardware.
The numbers matter for planning. 115GB of model files is a serious download and a serious disk footprint. The M5 Max with unified memory handles it, but this is not a casual install, and generation is measured in tens of minutes, not seconds.
How It Compares to the Native Video Race
MiniMax H3 ships with native dual-channel audio, which is a step beyond video models that produce silent clips and need a separate audio pass. Running that pipeline locally on Apple hardware is genuinely new.
For context, the broader AI video market in 2026 is dominated by cloud APIs. ByteDance’s Seedance 2.5, PixVerse, and others push strong models through hosted endpoints. A local option matters for confidentiality-sensitive work, offline workflows, and anyone who wants to avoid per-generation API costs.
The Cost and Performance Reality
Here is the honest part. Running a 115GB multimodal model locally is not a convenience play. The download, the disk space, and the generation time all point to serious hardware and patience.
The value is in what it enables: full control over generation, no per-clip API fees, and data that never leaves the machine. For studios, researchers, and teams with sensitive content, that tradeoff is often worth it.
Getting Started
If you want to try it, the path is the standard MLX workflow: install the package, download the model weights, and run generation with the documented commands. Expect the download to take a while, and expect the first generation to be slow while the model loads.
The practical recommendation: test with a short clip first, verify the output pipeline end to end, and only then commit to longer generation runs.
Related Reads
- [The AI Video Generation Race in 2026](https://getaibest.com/ai-video-generation-race-2026/)
- [MiniMax H3: Open Multimodal Model](https://getaibest.com/minimax-h3-open-multimodal-model/)
- [AirLLM: Running 70B Models on 4GB of VRAM](https://getaibest.com/airllm-70b-models-4gb-vram-local-ai/)