Moss Image SFT needs about 4.4 GB of memory at Q4_K_S (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 3.5 GB (Q4_K_S) to 5.7 GB (Q8_0).
5B text‑to‑image diffusion model fine‑tuned from MOSS‑Image‑Base
Moss Image SFT is a 5.08B parameter text‑to‑image diffusion transformer. It supports natural‑language prompts, tag sequences, and JSON layouts for precise text placement and object arrangement. The model requires a Qwen3.5‑9B text encoder, MOSS tokenizer, and MOSS/FLUX.2 VAE.
Good at
- Clear text grouping
- Organized whiteboard layouts
- JSON layout generation
Limits
- Requires Qwen3.5‑9B text encoder
- No vision support in the GGUF file
- Needs external VAE and tokenizer
Best for
- Generating instructional whiteboard images
- Creating layout‑driven illustrations
- Producing text‑rich artwork
Who it’s for. Users who need a fine‑tuned text‑to‑image model for detailed layout control. Ideal for developers integrating MOSS‑Image pipelines in ComfyUI or stable‑diffusion.cpp environments.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 3.5 GB | 4.4 GB | Fits | Get file → | |
| Q8_0 | 5.7 GB | 6.9 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_S quantization (file size 3.46 GB, estimated 4.4 GB memory at 8k context). If more VRAM is available, Q8_0 (5.71 GB, 6.9 GB memory) offers higher precision.
What GPU do you need for Moss Image SFT?
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_K_S (3.5 GB file, about 4.4 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 SFT quant should you choose?
Q4_K_S (3.5 GB) is the middle option in this repository. 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 SFT
How much VRAM does Moss Image SFT need?
About 4.4 GB at Q4_K_S with an 8K context window. That is the 3.5 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 Moss Image SFT 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 SFT GGUF?
It depends on the quant: Q4_K_S is 3.5 GB, Q8_0 is 5.7 GB.
Where can I download Moss Image SFT GGUF?
The files are on Hugging Face in the axiomofmind/Moss-Image-SFT-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 SFT 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 this model on 8 GB VRAM?
Yes, the Q4_K_S quantization requires about 4.4 GB VRAM at 8k context, which fits within 8 GB. Use --offload-to-cpu if needed.
What additional components are needed?
A Qwen3.5‑9B text encoder, the official MOSS tokenizer, and the MOSS/FLUX.2 VAE are required.
Does the GGUF file contain the VAE?
No, the GGUF contains only the diffusion transformer; the VAE must be supplied separately.