nightmare moss image needs about 4.1 GB of memory at Q4_0 (a 3.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.2 GB (Q4_0) to 3.3 GB (Q4_0).
Nightmare Moss Image – a 5.08B text‑to‑image model quantized to Q4_0
Nightmare Moss Image is a 5.08B parameter text‑to‑image model derived from OpenMOSS MOSS‑Image‑SFT. It is released under Apache‑2.0 and supports natural‑language prompts, tag sequences, and JSON layouts. The model is quantized to Q4_0 for efficient inference on limited‑memory devices.
Good at
- High‑quality text‑to‑image generation
- JSON layout control
- Fine‑tuned for clear text grouping
Limits
- No vision support
- Requires CUDA‑enabled NVIDIA GPU
- No integrated LoRA merging
Best for
- Generating detailed images from prompts
- Creating whiteboard layouts
- Producing images with structured text
Who it’s for. Developers building text‑to‑image pipelines on GPUs with limited VRAM. Researchers needing a lightweight, open‑source model for experimentation. Artists looking for precise layout control in generated images.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 3.2 GB | 4.1 GB | Fits | Get file → | |
| Q4_0 | 3.3 GB | 4.2 GB | Fits | Get file → |
For 8 GB VRAM, use the 3.22 GB Q4_0 GGUF file; estimated memory at 8 k context is 4.1 GB, which is within budget. If you have 4 GB VRAM, the 3.33 GB file uses 4.2 GB memory, which may be tight. No other quantizations are available.
What GPU do you need for nightmare moss 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 (3.3 GB file, about 4.2 GB in use).
Which nightmare moss image quant should you choose?
Q4_0 (3.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_0 at 3.2 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about nightmare moss image
How much VRAM does nightmare moss image need?
About 4.1 GB at Q4_0 with an 8K context window. That is the 3.2 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 nightmare moss image on an 8 GB GPU?
Yes, with Q4_0: the 3.3 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of nightmare moss image GGUF?
It depends on the quant: Q4_0 is 3.2 GB, Q4_0 is 3.2 GB, Q4_0 is 3.3 GB.
Where can I download nightmare moss image GGUF?
The files are on Hugging Face in the AbrahamPJ/nightmare-moss-image repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does nightmare moss 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 Nightmare Moss Image on 8 GB VRAM?
Yes, the 3.22 GB Q4_0 file uses approximately 4.1 GB memory at 8 k context, fitting within 8 GB VRAM.
Does the model support LoRA merging?
LoRA is applied at runtime and is not merged into the weights; merging would erase its effect.
What license applies to this model?
The model is released under the Apache‑2.0 license.