Python 包 PipeNetwork/minimax-h3-mlx 将其移植到 MLX,支持 Apple Silicon 运行。 作者在 M5 Max MacBook Pro 上实测,下载约 115 GB 模型文件,视频生成耗时不到 45 分钟。
PipeNetwork/minimax-h3-mlx:https://github.com/PipeNetwork/minimax-h3-mlx。MiniMax 两天前发布了 MiniMax-H3:https://huggingface.co/MiniMaxAI/MiniMax-H3,他们将其描述为“通用、多模态生成系统”,实际上意味着它可以接受文本、图像、音频和视频,并可以使用它们生成最长 15 秒的带音频视频片段。
这个 Python 包将它移植到 MLX,以便在 Apple Silicon 上运行。
我在我的 M5 Max MacBook Pro 上让它运行起来了。我克隆了仓库,然后像这样运行模型:
这是我根据该提示词生成的视频:
一只彩虹色的臭鼬跳过超市里的苔藓木头
您的浏览器不支持 HTML5 视频。
它下载了大约 115 GB 的模型文件,视频生成时间不到 45 分钟。
视频很令人印象深刻,但音频听起来像奇怪的语音垃圾,因为我没有提供任何关于音频应是什么样的提示。提示指南:https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md (我在这个实验之前没有阅读)有大量关于如何使其工作的详细信息。
这是 Simon Willison 于 2026 年 8 月 4 日发布的链接帖子:/2026/Aug/4/。
每月赞助我 10 美元,即可获得本月最重要的 LLM 发展的精选电子邮件摘要。
PipeNetwork/minimax-h3-mlx:https://github.com/PipeNetwork/minimax-h3-mlx . MiniMax released MiniMax-H3:https://huggingface.co/MiniMaxAI/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:
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:https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md (which I didn't read prior to this experiment) has a whole bunch of information on how to get this to work.
This is a link post by Simon Willison, posted on 4th August 2026:/2026/Aug/4/.
Sponsor me for $10/month and get a curated email digest of the month's most important LLM developments.