MOSS Image GGUFs needs about 4.6 GB of memory at Q4_K_M (a 3.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 20 quants, from 2.3 GB (Q2_K) to 5.7 GB (Q8_0).
5B‑parameter text‑to‑image diffusion transformer in GGUF format
MOSS Image GGUFs provide a 5.08‑billion‑parameter diffusion transformer for text‑to‑image generation. The weights are quantized by realrebelai and derived from OpenMOSS‑Team/MOSS‑Image‑SFT. They support natural‑language prompts, tag sequences, and JSON layouts for structured image creation.
Good at
- Natural‑language image prompts
- Tag‑style prompt control
- JSON layout generation
Limits
- Not a conversational LLM
- Requires a MOSS‑Image inference integration
- No vision support in the GGUF alone
Best for
- Local text‑to‑image experimentation
- ComfyUI image generation workflows
- Research on diffusion transformer quantization
Who it’s for. Users who want to run MOSS‑Image locally on consumer GPUs. The model is suitable for developers and researchers building or testing text‑to‑image pipelines that use the DiT architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.3 GB | 3.0 GB | Fits | Get file → | |
| Q2_K | 2.3 GB | 3.0 GB | Fits | Get file → | |
| Q3_K_S | 2.7 GB | 3.5 GB | Fits | Get file → | |
| Q3_K_S | 2.7 GB | 3.5 GB | Fits | Get file → | |
| Q3_K_M | 2.9 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_M | 2.9 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_L | 3.1 GB | 3.9 GB | Fits | Get file → | |
| Q3_K_L | 3.1 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_S | 3.5 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_S | 3.5 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_M | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q4_K_M | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_S | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_M | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q5_K_M | 4.1 GB | 5.1 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 → | |
| 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_K_S (file size 3.46 GB, estimated 4.4 GB memory). For 12 GB VRAM, Q5_K_M (4.11 GB, 5.1 GB memory) offers a good balance. If more VRAM is available, Q8_0 (5.71 GB, 6.9 GB memory) gives the highest quality.
What GPU do you need for MOSS Image GGUFs?
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: the best quant that fits is Q3_K_L (3.1 GB file, about 3.9 GB in use).
- 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 GGUFs quant should you choose?
Q4_K_M is the usual starting point for MOSS Image GGUFs: it balances file size and quality well. Here it is a 3.7 GB file.
The Q8_0 file is 5.7 GB, about 1.5 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 Q2_K at 2.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MOSS Image GGUFs
How much VRAM does MOSS Image GGUFs need?
About 4.6 GB at Q4_K_M with an 8K context window. That is the 3.7 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 GGUFs 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 GGUFs GGUF?
It depends on the quant: Q2_K is 2.3 GB, Q2_K is 2.3 GB, Q3_K_S is 2.7 GB, Q3_K_S is 2.7 GB, Q3_K_M is 2.9 GB, Q3_K_M is 2.9 GB and 14 more.
Where can I download MOSS Image GGUFs GGUF?
The files are on Hugging Face in the realrebelai/MOSS-Image_GGUFs 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 GGUFs 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 GGUF on 8 GB VRAM?
Yes, a Q4_K_S quantized file (3.46 GB) requires about 4.4 GB memory at 8k context, which fits 8 GB VRAM.
Does the GGUF include the text encoder?
No. The GGUF contains only the diffusion transformer; a separate Qwen3.5‑9B text encoder is required.
Is this model licensed for commercial use?
The model is licensed under apache‑2.0, which permits commercial use with attribution.