MOSS Image needs about 4.5 GB of memory at Q4_K_M (a 3.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 3.3 GB (Q4_0) to 5.7 GB (Q8_0).
MOSS Image – a 5.08B parameter text‑to‑image model in GGUF format
MOSS Image is a 5.08B parameter text‑to‑image model derived from OpenMOSS. It accepts natural‑language prompts, tag sequences, and JSON layouts to generate still images. The model is released under Apache‑2.0 and is available in several GGUF quantizations.
Good at
- Text‑driven image generation
- Layout‑based image creation
- Prompt enhancement via JSON
Limits
- No vision input support
- Requires CUDA‑enabled NVIDIA GPU
- No built‑in LoRA support
Best for
- Generating concept art from prompts
- Creating whiteboard layouts
- Automating prompt enhancement workflows
Who it’s for. Developers and artists who need a lightweight, open‑source text‑to‑image model for local inference. The model is suitable for integration into ComfyUI or custom pipelines that support GGUF quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q4_K_M | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q4_K_M | 3.6 GB | 4.5 GB | Fits | Get file → | |
| — | 3.8 GB | 4.8 GB | Fits | Get file → | |
| — | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 4.6 GB | 5.6 GB | Fits | Get file → | |
| Q6_K | 4.6 GB | 5.6 GB | Fits | Get file → | |
| — | 5.4 GB | 6.6 GB | Fits | Get file → | |
| — | 5.4 GB | 6.6 GB | Fits | Get file → | |
| Q8_0 | 5.7 GB | 6.9 GB | Fits | Get file → | |
| Q8_0 | 5.7 GB | 6.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (3.33 GB file, ~4.2 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (3.6 GB file, ~4.5 GB memory) or Q6_K (4.55 GB file, ~5.6 GB memory). For 16 GB VRAM, Q8_0 (5.71 GB file, ~6.9 GB memory) offers higher precision.
What GPU do you need for 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 Q6_K (4.6 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (5.7 GB file, about 6.9 GB in use).
Which MOSS Image quant should you choose?
Q4_K_M is the usual starting point for MOSS Image: it balances file size and quality well. Here it is a 3.6 GB file.
The Q8_0 file is 5.7 GB, about 1.6 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 Q4_0 at 3.3 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 MOSS Image
How much VRAM does MOSS Image need?
About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.6 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 MOSS Image on an 8 GB GPU?
Yes, with Q8_0: the 5.7 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MOSS Image GGUF?
It depends on the quant: Q4_0 is 3.3 GB, Q4_0 is 3.3 GB, Q4_K_M is 3.6 GB, Q4_K_M is 3.6 GB, file is 3.8 GB, file is 3.8 GB and 6 more.
Where can I download MOSS Image GGUF?
The files are on Hugging Face in the molbal/MOSS-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 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 MOSS Image on 8 GB VRAM?
Yes, the Q4_0 quantization uses 3.33 GB file size and requires about 4.2 GB VRAM at 8k context.
Does the model support vision input?
No, MOSS Image only accepts text prompts, tag sequences, or JSON layouts.
What license applies to the GGUF files?
The GGUF quantizations are released under the Apache‑2.0 license.