GG

GGUF v4

GgufGGUF by speach1sdef178Updated 2026-05-03
Download on Hugging Face
Parameters20.4B
Context—
Layers—
Architectureqwen_image
Smallest quant12.1 GB
Quick answer

GGUF v4 needs about 19.3 GB of memory at Q6_K (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 12.1 GB (Q4_K_S) to 21.8 GB.

GGUF v4 is a 20.4B-parameter Gguf model in GGUF format, quantized by speach1sdef178. The repository has 6 quant files, from 12.1 GB (Q4_K_S) to 21.8 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S12.1 GB 14.1 GB
Too big Get file →
—12.1 GB 14.1 GB
Too big Get file →
Q6_K16.8 GB 19.3 GB
Too big Get file →
Q6_K16.8 GB 19.3 GB
Too big Get file →
—21.8 GB 24.9 GB
Too big Get file →
—21.8 GB 24.9 GB
Too big Get file →

What GPU do you need for GGUF v4?

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 Q4_K_S (12.1 GB file, about 14.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (16.8 GB file, about 19.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (21.8 GB file, about 24.9 GB in use).

Which GGUF v4 quant should you choose?

Q6_K (16.8 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q4_K_S at 12.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen_image
Parameters20.4B

Source

Quantized byspeach1sdef178
FamilyGguf
Licenseapache-2.0
Downloads (HF)60
Last updated2026-05-03

Frequently asked questions about GGUF v4

How much VRAM does GGUF v4 need?

About 19.3 GB at Q6_K with an 8K context window. That is the 16.8 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 GGUF v4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of GGUF v4 GGUF?

It depends on the quant: Q4_K_S is 12.1 GB, file is 12.1 GB, Q6_K is 16.8 GB, Q6_K is 16.8 GB, file is 21.8 GB, file is 21.8 GB.

Where can I download GGUF v4 GGUF?

The files are on Hugging Face in the speach1sdef178/GGUF_v4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does GGUF v4 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.

Similar models

Browse all →

More Gguf models

All Gguf →

Other medium models

All medium models →