RE

bg replace preproc

ReplaceGGUF by ChicolllUpdated 2026-08-23
Download on Hugging Face
Parameters20.4B
Context—
Layers—
Architectureqwen_image
Smallest quant14.4 GB
Quick answer

bg replace preproc needs about 16.6 GB of memory at Q5_0 (a 14.4 GB file) with an 8K context window, so it fits on a 24 GB GPU.

bg replace preproc is a 20.4B-parameter Replace model in GGUF format, quantized by Chicolll. The repository has 1 quant file, from 14.4 GB (Q5_0) to 14.4 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_014.4 GB 16.6 GB
Too big Get file →

What GPU do you need for bg replace preproc?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_0 (14.4 GB file, about 16.6 GB in use).

Which bg replace preproc quant should you choose?

Q5_0 (14.4 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen_image
Parameters20.4B

Source

Quantized byChicolll
FamilyReplace
Downloads (HF)7
Last updated2026-08-23

Frequently asked questions about bg replace preproc

How much VRAM does bg replace preproc need?

About 16.6 GB at Q5_0 with an 8K context window. That is the 14.4 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 bg replace preproc on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of bg replace preproc GGUF?

It depends on the quant: Q5_0 is 14.4 GB.

Where can I download bg replace preproc GGUF?

The files are on Hugging Face in the Chicolll/bg-replace-preproc repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

Other medium models

All medium models →