PO

pony diffusion v6 xl

PonyGGUF by off-grid-aiUpdated 2026-10-21
Download on Hugging Face
Parameters3.47B
Context—
Layers—
Architecture—
Smallest quant2.8 GB
Quick answer

pony diffusion v6 xl needs about 3.6 GB of memory at Q4_K_S (a 2.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 2.8 GB (Q4_K) to 4.2 GB (Q8_0).

Pony Diffusion V6 XL – a 3.47B parameter SDXL finetune for pony and anthropomorphic imagery

Pony Diffusion V6 XL is a 3.47B parameter SDXL finetune that generates SFW and NSFW visuals of anthro, feral, or humanoid species. It accepts natural language prompts and a range of style tags. The model is designed for on‑device generation via stable‑diffusion.cpp.

Good at

  • High quality pony and anthropomorphic images
  • Supports a wide range of style and rating tags
  • Works well with clip skip 2 for best output

Limits

  • Requires clip skip 2 or -2 for quality
  • No negative prompts needed but not all SDXL features supported
  • License restricts commercial use

Best for

  • Generating pony themed art
  • Creating custom SDXL images with style tags
  • On‑device image generation with stable‑diffusion.cpp

Who it’s for. Artists and hobbyists who want to produce pony or anthropomorphic artwork locally. The model is suitable for users who prefer on‑device generation and can comply with the creativeml‑openrail‑m license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K2.8 GB 3.6 GB
Fits Get file →
Q4_K_S2.8 GB 3.6 GB
Fits Get file →
Q8_04.2 GB 5.2 GB
Fits Get file →

For 8 GB VRAM use the Q4_K or Q4_K_S quant, each 2.8 GB and needs about 3.6 GB RAM at 8 k context. For higher quality with 12 GB VRAM use Q8_0, 4.18 GB file and about 5.2 GB RAM at 8 k context. Memory estimates are approximate.

What GPU do you need for pony diffusion v6 xl?

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 Q4_K (2.8 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 5.2 GB in use).

Which pony diffusion v6 xl quant should you choose?

Q4_K_S (2.8 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_K at 2.8 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

Parameters3.47B

Source

Quantized byoff-grid-ai
FamilyPony
Downloads (HF)3,384
Last updated2026-10-21

Frequently asked questions about pony diffusion v6 xl

How much VRAM does pony diffusion v6 xl need?

About 3.6 GB at Q4_K_S with an 8K context window. That is the 2.8 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 pony diffusion v6 xl on an 8 GB GPU?

Yes, with Q8_0: the 4.2 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of pony diffusion v6 xl GGUF?

It depends on the quant: Q4_K is 2.8 GB, Q4_K_S is 2.8 GB, Q8_0 is 4.2 GB.

Where can I download pony diffusion v6 xl GGUF?

The files are on Hugging Face in the off-grid-ai/pony-diffusion-v6-xl-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does pony diffusion v6 xl use?

Hugging Face lists the license as creativeml-openrail-m. 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 this model on 8 GB VRAM?

Yes, the Q4_K and Q4_K_S quant files are 2.8 GB and require about 3.6 GB RAM at 8 k context, fitting within 8 GB VRAM.

Does this model support negative prompts?

It is designed to work without negative prompts; they are not required for most use cases.

What license does this model use?

The model is licensed under creativeml-openrail-m, which imposes usage restrictions.

Other GGUFs of Pony_Diffusion_V6_XL

Similar models

Browse all →

More from off-grid-ai

All by off-grid-ai →

More Pony models

All Pony →

Other tiny models

All tiny models →