BE

Bernini 1.3B ComfyUI

BerniniGGUF by neuregexUpdated 2026-06-10
Download on Hugging Face
Parameters1.42B
Context—
Layers—
Architecturewan
Smallest quant1.0 GB
Quick answer

Bernini 1.3B ComfyUI needs about 1.6 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 1.0 GB (Q4_K_M) to 4.1 GB (Q5_K_M).

Bernini 1.3B ComfyUI – lightweight video editing model

Bernini 1.3B is a single‑expert renderer fine‑tuned from Wan2.1‑1.3B. It runs on modest GPUs and supports style transfer, watermark removal, and local editing. The model is released under Apache‑2.0 and is part of the Bernini family.

Good at

  • Simple video edits such as style transfer
  • Watermark or subtitle removal
  • Local image editing

Limits

  • No vision support beyond the renderer
  • Limited performance on complex human generation
  • Requires CUDA GPU for optimal speed

Best for

  • ComfyUI users needing quick edits
  • Low‑budget GPU setups
  • Projects requiring open‑source licensing

Who it’s for. Developers and hobbyists who want a fast, open‑source video editing model that fits on 8‑16 GB VRAM. The model is ideal for those who prefer a single‑expert setup without the need for dual‑expert configurations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.0 GB 1.6 GB
Fits Get file →
Q5_K_M1.1 GB 1.7 GB
Fits Get file →
Q6_K1.2 GB 1.8 GB
Fits Get file →
Q8_01.5 GB 2.2 GB
Fits Get file →
Q5_K_M4.1 GB 5.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.98 GB, ~1.6 GB memory at 8k context). If 12 GB is available, Q5_K_M (1.09 GB, ~1.7 GB memory) is a good balance. For 24 GB cards, the larger Q8_0 (1.54 GB, ~2.2 GB memory) or the 4.15 GB Q5_K_M variant can be used for higher quality.

What GPU do you need for Bernini 1.3B 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: the best quant that fits is Q8_0 (1.5 GB file, about 2.2 GB in use).
  • 6 GB VRAM: the best quant that fits is Q5_K_M (4.1 GB file, about 5.1 GB in use).

Which Bernini 1.3B ComfyUI quant should you choose?

Q4_K_M is the usual starting point for Bernini 1.3B ComfyUI: it balances file size and quality well. Here it is a 1.0 GB file.

The Q8_0 file is 1.5 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturewan
Parameters1.42B

Source

Quantized byneuregex
FamilyBernini
Licenseapache-2.0
Downloads (HF)1,723
Last updated2026-06-10

Frequently asked questions about Bernini 1.3B ComfyUI

How much VRAM does Bernini 1.3B ComfyUI need?

About 1.6 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Bernini 1.3B ComfyUI on an 8 GB GPU?

Yes, with Q5_K_M: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bernini 1.3B ComfyUI GGUF?

It depends on the quant: Q4_K_M is 1.0 GB, Q5_K_M is 1.1 GB, Q6_K is 1.2 GB, Q8_0 is 1.5 GB, Q5_K_M is 4.1 GB.

Where can I download Bernini 1.3B ComfyUI GGUF?

The files are on Hugging Face in the neuregex/Bernini-1.3B-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 Bernini 1.3B ComfyUI use?

Hugging Face lists the license as apache-2.0. 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 Bernini 1.3B on an 8 GB GPU?

Yes, the Q4_K_M quantized model is 0.98 GB and requires approximately 1.6 GB VRAM at 8k context, fitting on an 8 GB GPU.

Does Bernini 1.3B support text‑to‑image generation?

No, Bernini 1.3B is a renderer for video editing and does not provide text‑to‑image capabilities.

What license does Bernini 1.3B use?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from neuregex

All by neuregex →

More Bernini models

All Bernini →

Other tiny models

All tiny models →