OpenVDN/vdn-minimax-h3 — new model trending #12 on Hugging Face
OpenVDN releases VDN-H3, an open hybrid-attention video model on MiniMax H3 that renders a 14.4-second 768p clip in 11.23 seconds on 8 B200 GPUs.
VDN-Minimax-H3 (VDN-H3) adds a frame-wise linear attention branch plus two LoRA adapters to MiniMax H3, distilled into 8-step and 50-step variants. It generates 768p, 14.4-second clips in 11.23 seconds on 8 B200 GPUs (90.5 seconds on one H200) using 8 denoising steps. Weights (about 82 GB total, including the 72 GB H3 base), the optimized inference stack, and training code are fully open-source under the MiniMax H3 Community License, which excludes the EU, UK, Korea, and US.
- Plug-and-play: linear branch and LoRA adapters merge at inference without touching backbone weights
- 8-step variant distilled from a 50-step model; distributed FP8 inference on B200s and H200s
- Prompts encoded with Qwen3-VL-32B; H3-Context-IR rewriting recommended for quality
- Inference path built on Diffusers, FlashAttention, and Triton
- Products
- VDN-H3MiniMax-H3
- AI models
- VDN-H3MiniMax-H3Qwen3-VL-32B
From the original article
4 min read at huggingface.co# Video DeltaNet: Hybrid Attention to Speed Up Video Models with Near-Lossless Quality [[`Blog`](https://openvdn. github. io/)] [[`Code`](https://github.
By OpenVDN · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.