# LingBot-Video puts a 30B MoE behind embodied AI video

> A DiT-based mixture-of-experts model activates just 3B parameters per step and ships under an Apache 2.0 license.

Published by The Open Weights on Jul 8, 2026. Canonical: https://theopenweights.com/news/lingbot-video-30b-a3b-h8nh

## Key facts

- Company: robbyant
- Model: LingBot-Video 30B-A3B
- Version: 1.0
- Category: Text → Video
- Modalities: Text → Video
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 30B (mixture of experts)
- Active parameters: 3B
- Architecture: LingBotVideoPipeline
- Significance: notable
- Published: 2026-07-08
- Last verified: 2026-07-12
- Hugging Face: https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b
- Canonical URL: https://theopenweights.com/news/lingbot-video-30b-a3b-h8nh

A new text-to-video model called **LingBot-Video 30B-A3B** has landed on Hugging Face, aimed squarely at embodied intelligence rather than general-purpose clip generation. The release pairs a diffusion transformer (DiT) backbone with a mixture-of-experts design, and it arrives under a permissive Apache 2.0 license ([model card](https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b)).

The naming tells the architectural story. Of its roughly 30 billion total parameters, only about 3 billion are active on any given forward pass — the "A3B" suffix. That sparse-activation approach is meant to give the model the capacity of a large network while keeping inference costs closer to those of a much smaller one.

## Why it matters

Most open video models chase cinematic prompts and short social clips. Framing this one as a pretraining model for embodied intelligence points at a different use case: generating and predicting visual sequences that robots and agents can learn from, where a world model that anticipates how a scene unfolds is more useful than a polished trailer.

A few things stand out about this release:

- **Sparse compute**: 30B total parameters with only 3B active, via MoE routing.
- **DiT foundation**: a diffusion transformer backbone, now the dominant design for high-quality video generation.
- **Open license**: Apache 2.0 permits commercial use and fine-tuning without downstream restrictions.

Several practical details — resolution, frame rate, and maximum clip duration — aren't specified in the release record, so teams evaluating LingBot-Video for robotics or simulation work will want to test those limits directly. As a version 1.0 initial release, it establishes a baseline that later checkpoints can build on.

## Get the model

- [Hugging Face](https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b)

## Sources

- [robbyant/lingbot-video-moe-30b-a3b](https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b) — Hugging Face, Jul 8, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "LingBot-Video puts a 30B MoE behind embodied AI video", The Open Weights, Jul 8, 2026, https://theopenweights.com/news/lingbot-video-30b-a3b-h8nh