@Modular: MiniMax designed H3 for hardware compatibility from the earliest stages, then opened the weights so people could run it…
Summary
MiniMax's H3 model is designed for broad hardware compatibility with open weights, and its implications for AI video will be discussed at the ModCon 2026 livestream event.
View Cached Full Text
Cached at: 08/14/26, 05:41 PM
MiniMax designed H3 for hardware compatibility from the earliest stages, then opened the weights so people could run it across even more silicon.
Morgan Suo, Head of US Business Development at @MiniMax_AI, joins ModCon ’26 to share what open-weight omni-context generation enables for AI video.
Aug 18, Grand Hyatt SF. Register for the livestream: https://luma.com/modcon-livestream…
ModCon 2026 Livestream · Luma
Source: https://luma.com/modcon-livestream Welcome! To join the event, please register below.
ModCon 2026, live from San Francisco. We’re streaming the mainstage all day, starting with the 9:00 AM PT keynote.
Chris Lattner and Tim Davis open with where Modular Platform stands today and what we’re building toward next. After that: a Modular Cloud deep dive, plus panels, fireside chats, and tech talks with leaders from across the AI stack.
Chat is open all day. Bring your questions about MAX, Mojo, and Modular Cloud.
The next-generation AI developer platform unifying the development and deployment of AI for the world.
Similar Articles
MiniMax H3 (10 minute read)
MiniMax launches H3, an open multimodal generation model that handles text, images, video, and audio, generating up to 15 seconds of 2K video with native stereo sound, and plans to open-source the weights.
MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video
MiniMax H3, a next-generation open-weights video model capable of generating 2K video with native stereo audio from text, images, video, or audio, launched with day-0 ComfyUI support and optimizations that allow it to run on consumer GPUs.
@RisingSayak: What a week for the open-weights community! The Diffusers team, hence, has been extremely busy at work > MiniMax H3: ht…
The Diffusers team announced several open-weight AI models including MiniMax H3, LTX 2.5, Wan Animate 2, and MiniMax Music 3, highlighting advancements in multimodal video and audio generation.
Anyone Used MiniMAx H3 yet? Open Weights are out today!
Open weights for MiniMAx H3 are out today; the author asks if anyone has tried using it to create in-between frames between key frames.
@PrajwalTomar_: China may have just had another DeepSeek moment, this time for AI video. MiniMax H3 is now open-weight: a powerful 33B …
MiniMax releases H3, a powerful open-weight 33B omni-modal video model supporting text, images, video, and audio, with local deployment on consumer GPUs and significantly lower cost than competitors like Seedance.