---
title: LingBot-30B-3B_GGUF_ComfyUI
canonical_url: "https://www.modelscope.cn/models/realrebelai/LingBot-30B-3B_GGUF_ComfyUI"
md_url: "https://www.modelscope.cn/models/realrebelai/LingBot-30B-3B_GGUF_ComfyUI.md"
repository: realrebelai/LingBot-30B-3B_GGUF_ComfyUI
last_updated: 2026-07-14
license: other
pipeline_tag: text-to-video-synthesis
tasks:
  - text-to-video-synthesis
base_model:
  - robbyant/lingbot-video-moe-30b-a3b
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 27
stars: 1
tags:
  - gguf
  - ggml
  - quantization
  - video
  - text-to-video
  - image-to-video
  - comfyui
  - moe
---

# LingBot-30B-3B_GGUF_ComfyUI

> LingBot-30B-3B_GGUF_ComfyUI - realrebelai 在 ModelScope 开源的模型。LingBot-Video-MoE-30B-A3B — GGUF (8GB-VRAM ready)

realrebelai/LingBot-30B-3B_GGUF_ComfyUI 是 ModelScope 魔搭社区上的text-to-video-synthesis模型，采用 other 许可，基于 robbyant/lingbot-video-moe-30b-a3b 构建。

- **Repository**: realrebelai/LingBot-30B-3B_GGUF_ComfyUI
- **License**: other
- **Tasks**: text-to-video-synthesis
- **Base model**: robbyant/lingbot-video-moe-30b-a3b
- **Tags**: gguf, ggml, quantization, video, text-to-video, image-to-video, comfyui, moe
- **Downloads**: 27
- **Stars**: 1
- **Last updated**: 2026-07-14

Source: https://www.modelscope.cn/models/realrebelai/LingBot-30B-3B_GGUF_ComfyUI

---

# LingBot-Video-MoE-30B-A3B — GGUF (8GB-VRAM ready)

<div align="center">
  <video 
    src="https://cdn-uploads.huggingface.co/production/uploads/68761990332d15464ccc8dee/LMOmadbPymaHITY4nvbcv.mp4" 
    width="400" 
    height="400" 
    autoplay 
    loop 
    muted 
    playsinline
  ></video>
</div>

<div align="center">
  <video 
    src="https://cdn-uploads.huggingface.co/production/uploads/68761990332d15464ccc8dee/lU2xwAF1Xu2EqU9te9DG0.mp4"
    width="400" 
    height="400" 
    autoplay 
    loop 
    muted 
    playsinline
  ></video>
</div>

## WARNING: Requires encoder and vae from 1.3b repo: https://huggingface.co/realrebelai/LingBot_ComfyUI/tree/main



GGUF quantizations of [robbyant/lingbot-video-moe-30b-a3b](https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b)
— a 128-expert Mixture-of-Experts text-to-video model — packaged to run on **consumer GPUs**
via **[ComfyUI_Rebels_LingBot](https://github.com/RealRebelAI/ComfyUI_Rebels_LingBot)**.
Tested on an **RTX 3070 8GB / 16GB RAM**.

## How a 30B runs on 8GB

MoE "A3B" means ~3B active params per token, but a diffusion forward touches essentially all
experts each step — so the win isn't compute, it's that **the weights never need to be
resident**. The node loader keeps the quantized bytes in system RAM (memmap-backed) and
dequantizes on demand: regular linears per forward, and the 128-expert fused stacks one
expert matrix at a time, only for routed experts. Peak VRAM stays within 8GB; system RAM (as
page cache) is what carries the model.

Because of this, **VRAM use is the same across all quant tiers** — you pick a tier by how
much RAM you have, not VRAM.

## Files

# DiT GGUF GOES IN DIFFUSION MODELS FOLDER!


| File | Size | Notes |
|---|---|---|
| `LingBot-Video-30B-A3B-Q3_K_M.gguf` | ~13 GB | Fits a 16GB machine's page cache → steps at RAM speed. Recommended for 16GB RAM. |
| `LingBot-Video-30B-A3B-Q4_K_M.gguf` | ~17 GB | Best quality/size for 32GB-RAM machines. |
| higher tiers (Q5/Q6/Q8) | 20–32 GB | Only worthwhile with large RAM. |

The expert tensors are quantized (not passed through at F16) — the fused 3D stacks are split
to per-expert 2D matrices during conversion so the quantizer compresses them properly.

Also required (from the base repo / companion 1.3B repo): `LingBot_vae.safetensors`, a
Qwen3-VL text encoder, and the 30B `transformer/config.json` (placed in the node pack's
`model_assets/` as `transformer_config_30b.json`).

## Usage

Load with the **LingBot 30B MoE Loader (GGUF)** node; the rest of the graph (Structured
Prompt → Text Encode → Sampler → Video Combine) is identical to the 1.3B workflow.

**The model requires structured JSON captions**, not prose — use the Structured Prompt node
and always set lighting, or output drifts dark. See the GitHub pack for the full workflow.

Expect the first chunk to be slow (weights streaming from disk, page cache cold); it speeds
up as the cache warms.

## License

**Other** — inherits the upstream LingBot-Video license from
[robbyant/lingbot-video-moe-30b-a3b](https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b);
see that repo's LICENSE before redistribution or commercial use. Quantization is a format
conversion only. Quants & nodes by [RealRebelAI](https://huggingface.co/realrebelai).