IM

Z Image

ImageGGUF by vantagewithaiUpdated 2026-01-30
Download on Hugging Face
Parameters6.15B
Context—
Layers—
Architecturelumina2
Smallest quant4.0 GB
Quick answer

Z Image needs about 6.1 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 14 quants, from 4.0 GB (Q2_K) to 12.3 GB (BF16).

Z Image – a 6.15B parameter image generation foundation model

Z Image is a 6.15B parameter foundation model for image generation. It is undistilled and supports full Classifier‑Free Guidance. The model is designed for high quality, diverse outputs across many visual styles.

Good at

  • High‑quality image generation
  • Robust prompt adherence
  • Wide stylistic coverage

Limits

  • No vision support
  • Requires 8k context for estimates
  • Apache‑2.0 license

Best for

  • Creative image generation
  • LoRA training base
  • ControlNet conditioning

Who it’s for. Developers and researchers who need a full‑capacity, undistilled image model for fine‑tuning or advanced prompt engineering.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.0 GB 5.0 GB
Fits Get file →
Q3_K_S4.3 GB 5.3 GB
Fits Get file →
Q3_K_M4.4 GB 5.5 GB
Fits Get file →
Q4_04.9 GB 6.0 GB
Fits Get file →
Q4_K_S4.9 GB 6.0 GB
Fits Get file →
Q4_K_M5.0 GB 6.1 GB
Fits Get file →
Q4_15.0 GB 6.1 GB
Fits Get file →
Q5_05.2 GB 6.3 GB
Fits Get file →
Q5_K_S5.2 GB 6.3 GB
Fits Get file →
Q5_15.3 GB 6.5 GB
Fits Get file →
Q5_K_M5.7 GB 6.9 GB
Fits Get file →
Q6_K6.7 GB 8.0 GB
Tight Get file →
Q8_07.2 GB 8.6 GB
Too big Get file →
BF1612.3 GB 14.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (≈6 GB memory). For 12 GB VRAM, Q5_0 or Q5_K_S (≈6.3 GB). For 16 GB VRAM, Q6_K (≈8 GB) or Q8_0 (≈8.6 GB). Memory estimates are approximate.

What GPU do you need for Z 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: the best quant that fits is Q4_0 (4.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 8.6 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (12.3 GB file, about 14.3 GB in use).

Which Z Image quant should you choose?

Q4_K_M is the usual starting point for Z Image: it balances file size and quality well. Here it is a 5.0 GB file.

The Q8_0 file is 7.2 GB, about 1.4 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 Q2_K at 4.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturelumina2
Parameters6.15B

Source

Quantized byvantagewithai
FamilyImage
Licenseapache-2.0
Downloads (HF)663
Last updated2026-01-30

Frequently asked questions about Z Image

How much VRAM does Z Image need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Image on an 8 GB GPU?

Yes, with Q6_K: the 6.7 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Z Image GGUF?

It depends on the quant: Q2_K is 4.0 GB, Q3_K_S is 4.3 GB, Q3_K_M is 4.4 GB, Q4_0 is 4.9 GB, Q4_K_S is 4.9 GB, Q4_K_M is 5.0 GB and 8 more.

Where can I download Z Image GGUF?

The files are on Hugging Face in the vantagewithai/Z-Image-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 Z Image 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 Image on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantizations which use about 6 GB of VRAM at 8k context.

Does Z Image support negative prompting?

Yes, it has robust negative control and responds well to negative prompts.

Is Z Image suitable for LoRA training?

Yes, its undistilled nature makes it an ideal base for LoRA and other fine‑tuning methods.

Similar models

Browse all →

More from vantagewithai

All by vantagewithai →

More Image models

All Image →

Other small models

All small models →