MiniMax H3 Omni-Modal Model Hits Hugging Face with Native 2K Stereo Video
victormustar · x · 2026-08-03
MiniMax has released MiniMax H3, a general-purpose omni-modal generative system, on Hugging Face. The model unifies multimodal context understanding across text, images, video, and audio, demonstrating broad comprehension and generation capabilities at the pre-training stage.
Key Specifications & Features:
- Video Output: 4–15 seconds duration, default 24 FPS, supports various aspect ratios (21:9 to 9:16), with a default short-side resolution of 768 pixels (2K generation supported via a specific variant).
- Native Audio: Generates 32 kHz stereo audio for synchronized audio-visual content.
- Multilingual: Stable conversational support for 11 languages including Chinese, English, Japanese, Korean, and French.
- Flexible Inputs: Offers multiple variants like First-and-last-frame mode (FL2VA), supporting complex inputs ranging from text-only to mixed audio-visual instructions.
Related event: MiniMax open-sources 33B multimodal video model H3(35 posts)→
More from Models
- Meta open-sources Muse Spark weights, Zuckerberg thanks Apple on X — AIFlow_ML · 2026-10-16
- Users report Gemini's memories can't actually be deleted even after wiping chat history — ThrowRA_Purpose2025 · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16