MiniMax-H3 MLX 移植版可在 Apple Silicon 上生成 15 秒带声视频
MiniMax-H3 出了 MLX 版，Apple Silicon 本地能跑，能生成 15 秒带声视频。
MiniMax 两天前发布 MiniMax-H3，称其为通用全模态生成系统，可输入文本、图像、音频和视频，输出最长 15 秒、含音频的视频片段。
PipeNetwork 的 Python 包将其移植到 MLX，让该模型可以在 Apple Silicon 上运行。Simon Willison 在 M5 Max MacBook Pro 上跑通，下载约 115GB 模型文件，生成一段视频耗时不到 45 分钟。
他提醒，若不参照 MiniMax-H3 的提示词指南指定音频方向，生成的声音可能像无意义的语音噪声。
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
This report is categorized under AITOP's "How-to" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include MiniMax-H3, MLX, 视频生成, 多模态.
Source attribution: curated from Simon Willison’s Weblog. Cross-source corroboration: 7 independent sources have covered this development (including Hailuo AI, IT之家, Justine Moore), confirming industry-wide signal strength.
