Run MiniMax-H3 Locally with SGLang Diffusion on 2× RTX 5090s or 1× RTX Pro 6000

MiniMax AI released MiniMax-H3, an open video generation model, with day-0 serving support in SGLang Diffusion, matching Seedance 2.0 at one-third the cost or free locally on 2x RTX 5090 or 1 RTX Pro 6000. The model processes text, image, video, and audio in a single context, generating 5-15 second clips at native 2K, 24fps with stereo audio, and runs on NVIDIA Blackwell, Hopper, and AMD MI355X/MI300X.

@MiniMax AI https://x.com/MiniMax AI H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, precise video edits, animation and stylized visuals, all locally on your own machine. No API bill, no waitlist. H3 takes text, image, video and audio in a single context, and generates 5-15s clips at native 2K, 24fps with native stereo audio. SGLang Diffusion also runs on @NVIDIAAI https://x.com/NVIDIAAI Blackwell and Hopper, and @AMD https://x.com/AMD MI355X / MI300X. Let's create something with MiniMax H3 👇 MiniMax-H3 Is Now Publicly Available