HA

hassaku-xl-illustrious.fp16.gguf

HassakuGGUF by void-gryphUpdated 2026-02-17
Download on Hugging Face
Parameters2.57B
Context77
Layers20
Architecturesdxl
Smallest quant1.4 GB
Quick answer

hassaku-xl-illustrious.fp16.gguf needs about 2.1 GB of memory at Q4_K_M (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.4 GB (Q4_K_M) to 2.7 GB (Q8_0).

Hassaku XL (Illustrious) – 2.57B SDXL model in GGUF format

Hassaku XL (Illustrious) is a 2.57B SDXL model optimized for low‑memory inference. It is available in multiple GGUF quantizations and supports image generation with a bright anime style.

Good at

  • Anime‑style image generation
  • Low‑memory inference
  • High detail preservation

Limits

  • No vision support
  • Small trained context of 77 tokens
  • License is other

Best for

  • Stable Diffusion web UI deployment
  • ComfyUI pipelines
  • Local inference on modest GPUs

Who it’s for. Developers and artists who need a lightweight SDXL model for anime‑style image creation. The model is suitable for local inference on GPUs with limited VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M1.4 GB 1.9 GB
Fits Get file →
Q5_K_M1.8 GB 2.3 GB
Fits Get file →
Q8_02.7 GB 3.2 GB
Fits Get file →

For 8 GB VRAM, use the Q4_K_M quantization (file size 1.45 GB, estimated memory 2.1 GB at 8 k context). If more VRAM is available, Q5_K_M (1.77 GB, 2.5 GB) or Q8_0 (2.73 GB, 3.6 GB) can be used for higher precision. Estimates are approximate.

What GPU do you need for hassaku-xl-illustrious.fp16.gguf?

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 (2.7 GB file, about 3.6 GB in use).

Which hassaku-xl-illustrious.fp16.gguf quant should you choose?

Q4_K_M is the usual starting point for hassaku-xl-illustrious.fp16.gguf: it balances file size and quality well. Here it is a 1.4 GB file.

The Q8_0 file is 2.7 GB, about 1.9 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

Architecturesdxl
Parameters2.57B
Layers20
Trained context77 tokens

Source

Quantized byvoid-gryph
FamilyHassaku
Licenseother
Downloads (HF)1,046
Last updated2026-02-17

Frequently asked questions about hassaku-xl-illustrious.fp16.gguf

How much VRAM does hassaku-xl-illustrious.fp16.gguf need?

About 2.1 GB at Q4_K_M with an 8K context window. That is the 1.4 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 hassaku-xl-illustrious.fp16.gguf on an 8 GB GPU?

Yes, with Q8_0: the 2.7 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of hassaku-xl-illustrious.fp16.gguf GGUF?

It depends on the quant: Q4_K_M is 1.4 GB, Q5_K_M is 1.8 GB, Q8_0 is 2.7 GB.

What context length does hassaku-xl-illustrious.fp16.gguf support?

The GGUF header lists a trained context length of 77 tokens (77).

Where can I download hassaku-xl-illustrious.fp16.gguf GGUF?

The files are on Hugging Face in the void-gryph/hassaku-xl-illustrious-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 hassaku-xl-illustrious.fp16.gguf use?

Hugging Face lists the license as other. 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 Hassaku XL on 8 GB VRAM?

Yes, the Q4_K_M quantization requires about 2.1 GB of VRAM at 8 k context, which fits within an 8 GB GPU.

Does this model support text‑to‑image only?

The model is designed for image generation; it does not include vision or text‑to‑image‑to‑image capabilities.

What is the trained context length?

The model was trained with a context of 77 tokens, so longer prompts may not be fully supported.

Similar models

Browse all →

More from void-gryph

All by void-gryph →

Other tiny models

All tiny models →