---
title: "MiniMax-H3 Ported to MLX, Runs on Apple Silicon to Generate Videos with Audio"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Aug/4/minimax-h3-mlx/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_0b96c123f27eddb9a65c0152"
published: "2026-08-04T19:10:09.000Z"
score: 72
channel: "ai"
tags: ["MiniMax","MiniMax-H3","MLX","Text-to-Video Generation"]
---

# MiniMax-H3 Ported to MLX, Runs on Apple Silicon to Generate Videos with Audio

## AI commentary

> This is worth watching because it shows the feasibility of open-source multimodal models on consumer hardware, good news for developers without high-end GPUs. If you build local AI tools or video generation and own an Apple Silicon device, this project is worth trying immediately.

## At a glance

Simon Willison blogged about PipeNetwork/minimax-h3-mlx, a port of MiniMax-H3, released two days ago as a general-purpose omni-modal generative system, to the MLX framework for Apple Silicon. He tested it on an M5 Max MacBook Pro, downloading ~115GB of model files and generating a 15-second video with audio in just under 45 minutes. The video is impressive, but the audio sounds like weird speech-like garbage because no prompt guidance was provided for audio. He notes that the prompting guide offers tips for better results.

## Key points

- MiniMax-H3 accepts text, images, audio, and video inputs, and can generate up to 15-second video clips with audio.
- PipeNetwork/minimax-h3-mlx ports it to MLX for running on Apple Silicon.
- Real-world test: ~115GB download, ~45 min generation; video is impressive but audio needs guidance from the prompting guide.

## Full text

PipeNetwork/minimax-h3-mlx MiniMax released MiniMax-H3 two days ago - they describe it as a "a general-purpose, omni-modal generative system", which in practice means it accepts text, images, audio and video and can use them to generate up to 15 second video clips with audio included. This Python package ports it to MLX for running on Apple Silicon. I got it running on my M5 Max MacBook Pro. I cloned the repo and ran the model like this: # First download the models uvx --from huggingface_hub hf download MiniMaxAI/MiniMax-H3 \ --include 'FL2VA/*' --exclude 'FL2VA/transformer/*' uvx --from huggingface_hub hf download pipenetwork/MiniMax-H3-MLX-8bit # Now run the prompt uv run --with mlx-vlm \ --with-requirements requirements.txt python scripts/generate.py \ "a rainbow colored skunk leaps over a mossy log in a supermarket" \ -o skunk.mp4 \ -c ~/.cache/huggingface/hub/models--MiniMaxAI--MiniMax-H3/snapshots/fa9c8ab1eaa21c8ae25e7e40b83b2e6002f340af/FL2VA \ -t ~/.cache/huggingface/hub/models--pipenetwork--MiniMax-H3-MLX-8bit/snapshots/3ac52081470b0488921c3ec3ba84a39097bf2361 Here's the video I got for the prompt: a rainbow colored skunk leaps over a mossy log in a supermarket Your browser does not support HTML5 video. It downloaded ~115 GB of model files, and the video generation took just under 45 minutes. The video is impressive, but the audio is weird speech-like garbage, because I didn't provide any prompt guidance as to what the audio should be. The prompting guide (which I didn't read prior to this experiment) has a whole bunch of information on how to get this to work. Tags: ai, generative-ai, mlx, text-to-video, minimax

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_0b96c123f27eddb9a65c0152