---
title: "MiniMax-H3 开源模型移植到 MLX，可在 Apple Silicon 上生成带音频视频"
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","文本生成视频"]
---

# MiniMax-H3 开源模型移植到 MLX，可在 Apple Silicon 上生成带音频视频

## AI 点评

> 这篇值得关注，因为它展示了开源多模态模型在消费级硬件上的可行性，对没有高端 GPU 的开发者来说是个好消息。如果你是做本地 AI 工具或视频生成的，手上有 Apple Silicon 设备，这个项目值得立刻尝试。

## 速览

Simon Willison 在博客中介绍了 PipeNetwork/minimax-h3-mlx 项目，该项目将 MiniMax 两天前发布的通用全模态生成系统 MiniMax-H3 移植到 MLX 框架，使其能在 Apple Silicon 上运行。他使用 M5 Max MacBook Pro 实测，下载约 115GB 模型文件，耗时近 45 分钟生成了一段 15 秒的带音频视频。视频质量不错，但音频因未做提示词引导而呈现类似语音的杂音。作者提醒需阅读官方提示词指南以获得更好效果。

## 关键点

- MiniMax-H3 可接受文本、图像、音频和视频输入，并生成最长 15 秒的带音频视频片段。
- PipeNetwork/minimax-h3-mlx 项目将其移植到 MLX，支持 Apple Silicon 本地运行。
- 实测下载约 115GB 模型，生成耗时约 45 分钟；视频效果不错，但音频需按提示词指南引导。

## 全文

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

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_0b96c123f27eddb9a65c0152