LI

LingBot 30B 3B GGUF ComfyUI

LingbotGGUF by realrebelaiUpdated 2026-07-12
Download on Hugging Face
Parameters30B
Context—
Layers—
Architecturewan
Smallest quant13.0 GB
Quick answer

LingBot 30B 3B GGUF ComfyUI needs about 19.6 GB of memory at Q4_K_M (a 17.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 13.0 GB (Q3_K_M) to 17.0 GB (Q4_K_M).

LingBot 30B 3B GGUF ComfyUI – 30B MoE text‑to‑video model for consumer GPUs

LingBot 30B 3B is a 30‑billion‑parameter Mixture‑of‑Experts text‑to‑video model. It is quantized to GGUF for use with ComfyUI and runs on consumer GPUs with 8 GB VRAM. The model requires structured JSON captions and external encoder and VAE files.

Good at

  • Video generation from structured prompts
  • Efficient MoE inference on 8 GB VRAM
  • Low VRAM footprint with high active parameters

Limits

  • Requires external encoder and VAE
  • No vision support in the GGUF file
  • No license details provided

Best for

  • Generating short video clips
  • Research on MoE video models
  • Testing on consumer GPUs

Who it’s for. Developers and researchers who need a 30B text‑to‑video model that can run on 8 GB VRAM. The model is suitable for experimentation with MoE architectures and structured prompt workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M13.0 GB 15.1 GB
Too big Get file →
Q4_K_M17.0 GB 19.6 GB
Too big Get file →

For 8 GB VRAM, the Q3_K_M quantization (13.01 GB file, ~15.1 GB RAM at 8k context) is recommended. If more system RAM is available, Q4_K_M (17.03 GB file, ~19.6 GB RAM) provides higher precision. Both keep VRAM usage within 8 GB.

What GPU do you need for LingBot 30B 3B GGUF ComfyUI?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q3_K_M (13.0 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (17.0 GB file, about 19.6 GB in use).

Which LingBot 30B 3B GGUF ComfyUI quant should you choose?

Q4_K_M is the usual starting point for LingBot 30B 3B GGUF ComfyUI: it balances file size and quality well. Here it is a 17.0 GB file.

If memory is tight, the smallest file is Q3_K_M at 13.0 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewan
Parameters30B

Source

Quantized byrealrebelai
FamilyLingbot
Licenseother
Downloads (HF)2,737
Last updated2026-07-12

Frequently asked questions about LingBot 30B 3B GGUF ComfyUI

How much VRAM does LingBot 30B 3B GGUF ComfyUI need?

About 19.6 GB at Q4_K_M with an 8K context window. That is the 17.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run LingBot 30B 3B GGUF ComfyUI on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of LingBot 30B 3B GGUF ComfyUI GGUF?

It depends on the quant: Q3_K_M is 13.0 GB, Q4_K_M is 17.0 GB.

Where can I download LingBot 30B 3B GGUF ComfyUI GGUF?

The files are on Hugging Face in the realrebelai/LingBot-30B-3B_GGUF_ComfyUI repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does LingBot 30B 3B GGUF ComfyUI use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run LingBot 30B on an RTX 3070 8GB GPU?

Yes, the model is designed for 8 GB VRAM. It uses system RAM for the quantized weights, keeping peak VRAM below 8 GB.

What additional files are needed to run the model?

You need the LingBot_vae.safetensors, a Qwen3‑VL text encoder, and the transformer/config.json from the base repo.

Does the model support vision input?

No, the GGUF file does not include vision support; it requires structured JSON captions only.

Other GGUFs of lingbot-video-moe-30b-a3b

Similar models

Browse all →

More from realrebelai

All by realrebelai →

More Lingbot models

All Lingbot →

Other medium models

All medium models →