Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75 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 8 quants, from 2.1 GB (Q3_K_M) to 8.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Z-Image-Engineer V6: a 4B Qwen3 text encoder for prompt enhancement
Z-Image-Engineer V6 is a SMART DoRA fine‑tuned 4B Qwen3 text encoder derived from Tongyi-MAI/Z-Image-Turbo. It is designed for local prompt enhancement in ComfyUI, LM Studio, and CLIPLoaderGGUF workflows. The model is released under Apache‑2.0 and supports only text encoding.
Good at
- Prompt enhancement for image generation
- Local text‑encoder replacement
- ComfyUI‑compatible loading
Limits
- No vision support
- Requires 8K context for full performance
- Large VRAM needed for higher quants
Best for
- Fine‑tuning image generation pipelines
- Prompt rewriting in ComfyUI
- LM Studio local prompt enhancement
Who it’s for. Users who need a lightweight, quantized text encoder for image generation workflows. Ideal for artists and developers working with ComfyUI or LM Studio who want consistent prompt conditioning without external servers.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 2.1 GB | 3.8 GB | Fits | Get file → | |
| MXFP4 | 2.3 GB | 4.0 GB | Fits | Get file → | |
| — | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q5_K_M | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q6_K | 3.3 GB | 5.0 GB | Fits | Get file → | |
| Q8_0 | 4.3 GB | 6.0 GB | Fits | Get file → | |
| F16 | 8.1 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_M (2.08 GB file, ~3.8 GB RAM). For 12 GB VRAM, Q4_K_M (2.5 GB file, ~4.2 GB RAM) offers a good balance. If more VRAM is available, Q5_K_M or Q6_K provide higher precision at ~4.6–5 GB RAM.
What GPU do you need for Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75?
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: the best quant that fits is MXFP4 (2.3 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.1 GB file, about 9.8 GB in use).
Which Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75 quant should you choose?
Q4_K_M is the usual starting point for Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75: 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.
If memory is tight, the smallest file is Q3_K_M at 2.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75
How much VRAM does Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75 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-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75 on an 8 GB GPU?
Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75 GGUF?
It depends on the quant: Q3_K_M is 2.1 GB, MXFP4 is 2.3 GB, file is 2.5 GB, Q4_K_M is 2.5 GB, Q5_K_M is 2.9 GB, Q6_K is 3.3 GB and 2 more.
What context length does Z-Image-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75 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-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75 GGUF?
The files are on Hugging Face in the BennyDaBall/Z-Image-Engineer-V6-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-Engineer-V6-SMART-DoRA-StyleBlendV9-25V17-75 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 Q4_K_M on 8 GB VRAM?
No, Q4_K_M requires about 4.2 GB RAM at 8K context, which exceeds 8 GB VRAM when combined with model weights.
Does this model support image generation?
No, it is a text encoder only; it does not generate images directly.
What license applies to this model?
The model is released under the Apache‑2.0 license.