IM

Z Anime

ImageGGUF by SeeSee21Updated 2026-04-27
Download on Hugging Face
Parameters6.15B
Context—
Layers—
Architecturelumina2
Smallest quant4.5 GB
Quick answer

Z Anime needs about 5.6 GB of memory at Q4_K_S (a 4.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 4.5 GB (Q4_K_S) to 7.2 GB (Q8_0).

Full anime fine‑tune of Z‑Image, 6.15B parameters

Z‑Anime is a full fine‑tune of Alibaba’s Z‑Image base model, built on the S3‑DiT architecture. It delivers rich anime aesthetics, strong diversity, and full negative prompt support. The model is ready for LoRA training and works with natural language prompts.

Good at

  • Anime‑style generation
  • High diversity in characters and poses
  • Full negative prompt support

Limits

  • No vision support
  • Requires 8GB VRAM for full model
  • No LoRA merges, only full fine‑tune

Best for

  • Anime illustration creation
  • Creative exploration of anime styles
  • Fine‑tuning for custom anime models

Who it’s for. Artists, researchers, and developers who need a robust anime generation base. The model is ideal for those who want to build or extend anime‑focused diffusion workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S4.5 GB 5.6 GB
Fits Get file →
Q8_07.2 GB 8.6 GB
Too big Get file →

For 8GB VRAM, use the Q4_K_S variant (~4.51 GB). For higher quality with more memory, the Q8_0 variant (~7.22 GB) is available. Memory estimates are approximate and depend on context size.

What GPU do you need for Z Anime?

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: the best quant that fits is Q4_K_S (4.5 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_S (4.5 GB file, about 5.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 8.6 GB in use).

Which Z Anime quant should you choose?

Q4_K_S (4.5 GB) is the middle option in this repository. 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

Architecturelumina2
Parameters6.15B

Source

Quantized bySeeSee21
FamilyImage
Licenseapache-2.0
Downloads (HF)2,237
Last updated2026-04-27

Frequently asked questions about Z Anime

How much VRAM does Z Anime need?

About 5.6 GB at Q4_K_S with an 8K context window. That is the 4.5 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 Z Anime on an 8 GB GPU?

Yes, with Q4_K_S: the 4.5 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Z Anime GGUF?

It depends on the quant: Q4_K_S is 4.5 GB, Q8_0 is 7.2 GB.

Where can I download Z Anime GGUF?

The files are on Hugging Face in the SeeSee21/Z-Anime repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Z Anime 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.

Can I run Z‑Anime on 8 GB VRAM?

Yes, the Q4_K_S quantized model (~4.51 GB) fits within 8 GB VRAM, leaving room for other processes.

Does Z‑Anime support vision prompts?

No, Z‑Anime is an image generation model and does not process vision inputs.

Is Z‑Anime a LoRA merge?

No, it is a full fine‑tune of the Z‑Image base, not a LoRA merge.

Other GGUFs of Z-Image

Similar models

Browse all →

More from SeeSee21

All by SeeSee21 →

More Image models

All Image →

Other small models

All small models →