DI

NL Diffusion Image

DiffusionGGUF by realrebelaiUpdated 2026-07-09
Download on Hugging Face
Parameters9.74B
Context—
Layers—
Architecturenldiff
Smallest quant5.7 GB
Quick answer

NL Diffusion Image needs about 6.9 GB of memory at Q4_K_M (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 5.7 GB (Q4_K_S) to 19.5 GB (F16).

NL Diffusion Image is a 9.74B-parameter Diffusion model in GGUF format, quantized by realrebelai. The repository has 8 quant files, from 5.7 GB (Q4_K_S) to 19.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S5.7 GB 6.9 GB
Fits Get file →
Q4_K_M5.7 GB 6.9 GB
Fits Get file →
—6.8 GB 8.1 GB
Too big Get file →
Q5_K_S6.9 GB 8.2 GB
Too big Get file →
Q5_K_M6.9 GB 8.2 GB
Too big Get file →
Q6_K8.1 GB 9.6 GB
Too big Get file →
Q8_010.5 GB 12.2 GB
Too big Get file →
F1619.5 GB 22.3 GB
Too big Get file →

What GPU do you need for NL Diffusion Image?

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: the best quant that fits is Q4_K_M (5.7 GB file, about 6.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.1 GB file, about 9.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (10.5 GB file, about 12.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (19.5 GB file, about 22.3 GB in use).

Which NL Diffusion Image quant should you choose?

Q4_K_M is the usual starting point for NL Diffusion Image: it balances file size and quality well. Here it is a 5.7 GB file.

The Q8_0 file is 10.5 GB, about 1.8 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.

If memory is tight, the smallest file is Q4_K_S at 5.7 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

Architecturenldiff
Parameters9.74B

Source

Quantized byrealrebelai
FamilyDiffusion
Downloads (HF)81
Last updated2026-07-09

Frequently asked questions about NL Diffusion Image

How much VRAM does NL Diffusion Image need?

About 6.9 GB at Q4_K_M with an 8K context window. That is the 5.7 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 NL Diffusion Image on an 8 GB GPU?

Yes, with Q4_K_M: the 5.7 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NL Diffusion Image GGUF?

It depends on the quant: Q4_K_S is 5.7 GB, Q4_K_M is 5.7 GB, file is 6.8 GB, Q5_K_S is 6.9 GB, Q5_K_M is 6.9 GB, Q6_K is 8.1 GB and 2 more.

Where can I download NL Diffusion Image GGUF?

The files are on Hugging Face in the realrebelai/NL-Diffusion-Image_GGUF 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 →

More from realrebelai

All by realrebelai →

More Diffusion models

All Diffusion →

Other medium models

All medium models →