IM

z image solordz v2

ImageGGUF by gimly13Updated 2026-10-04
Download on Hugging Face
Parameters6.15B
Context40K
Layers36
Architectureqwen3
Smallest quant2.5 GB
Quick answer

z image solordz v2 needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 10 quants, from 2.5 GB (Q4_K_M) to 7.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Z Image Solordz v2 – 6.15B Qwen3 image model in 8‑step turbo mode

Z Image Solordz v2 is a 6.15B parameter Qwen3 image model quantized to GGUF. It operates in turbo mode with 8 diffusion steps and CFG=1, ignoring negative prompts. The bundle includes a companion text encoder and VAE for full functionality.

Good at

  • Fast 8‑step generation
  • High detail in complex scenes
  • Strong prompt adherence

Limits

  • No negative prompt support
  • Requires companion text encoder
  • Large VRAM needed for higher quants

Best for

  • Rapid image generation in ComfyUI
  • Low‑latency inference on GPUs
  • Batch processing with 8‑step workflow

Who it’s for. Users needing quick image generation with high detail. Ideal for developers integrating Z‑Image into ComfyUI or stable‑diffusion.cpp workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q5_K_M2.9 GB 4.6 GB
Fits Get file →
Q6_K3.3 GB 5.0 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
Q3_K4.3 GB 6.0 GB
Fits Get file →
Q4_K_S4.8 GB 6.5 GB
Fits Get file →
Q4_K5.2 GB 6.9 GB
Fits Get file →
Q5_K5.7 GB 7.4 GB
Tight Get file →
Q6_K6.0 GB 7.8 GB
Tight Get file →
Q8_07.3 GB 9.0 GB
Too big Get file →

For 8 GB VRAM, use diffusion Q4_K (5.15 GB) with text encoder Q4_K_M (2.5 GB). For 12 GB VRAM, Q5_K_M (2.89 GB) is a good balance. Higher quants like Q6_K (3.31 GB) need 16 GB or more.

What GPU do you need for z image solordz v2?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 Q3_K (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 9.0 GB in use).

Which z image solordz v2 quant should you choose?

Q4_K_M is the usual starting point for z image solordz v2: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 GB, about 1.7 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

Architectureqwen3
Parameters6.15B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized bygimly13
FamilyImage
Downloads (HF)2,758
Last updated2026-10-04

Frequently asked questions about z image solordz v2

How much VRAM does z image solordz v2 need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 image solordz v2 on an 8 GB GPU?

Yes, with Q6_K: the 6.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of z image solordz v2 GGUF?

It depends on the quant: Q4_K_M is 2.5 GB, Q5_K_M is 2.9 GB, Q6_K is 3.3 GB, Q8_0 is 4.3 GB, Q3_K is 4.3 GB, Q4_K_S is 4.8 GB and 4 more.

What context length does z image solordz v2 support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download z image solordz v2 GGUF?

The files are on Hugging Face in the gimly13/z-image-solordz-v2-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 solordz v2 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, use diffusion Q4_K (5.15 GB) and text encoder Q4_K_M (2.5 GB).

Does the model support negative prompts?

No, it ignores negative prompts; all exclusions must be in the positive prompt.

What sampler settings are recommended?

First pass er_sde/beta, second pass euler/simple; euler/normal for realism, euler_a/normal for art.

Similar models

Browse all →

More from gimly13

All by gimly13 →

More Image models

All Image →

Other small models

All small models →