Diffusion Models needs about 14.8 GB of memory at Q8_0 (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 11 quants, from 6.8 GB to 21.8 GB (Q8_0).
Diffusion Models – a 11.9B‑parameter flux architecture
Diffusion Models is a 11.9 billion parameter flux model. It is available in multiple GGUF quantizations. The model has no explicit context token limit or language restrictions listed.
Good at
- Image generation
- Text‑to‑image synthesis
- Creative visual content
Limits
- No vision support specified
- No context token limit info
- License not provided
Best for
- Artists needing high‑quality image prompts
- Developers building creative AI tools
- Researchers exploring diffusion models
Who it’s for. This model is suitable for users who want a large flux‑based diffusion model in GGUF format. It is ideal for those who can manage the memory requirements of the various quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_S | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q2_K | 7.1 GB | 8.4 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.7 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.7 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.8 GB | Too big | Get file → | |
| Q5_1 | 15.4 GB | 17.7 GB | Too big | Get file → | |
| Q6_K | 16.8 GB | 19.3 GB | Too big | Get file → | |
| Q6_K | 16.8 GB | 19.3 GB | Too big | Get file → | |
| Q8_0 | 21.8 GB | 24.9 GB | Too big | Get file → | |
| Q8_0 | 21.8 GB | 24.9 GB | Too big | Get file → |
For 8‑GB VRAM, use Q4_K_S (6.81 GB file, 8.1 GB memory). For 12‑GB VRAM, Q2_K (7.06 GB file, 8.4 GB memory) or Q8_0 (12.71 GB file, 14.7 GB memory). For 24‑GB VRAM, Q6_K (16.82 GB file, 19.3 GB memory) or Q8_0 (21.76 GB file, 24.9 GB memory). Estimates are approximate.
What GPU do you need for Diffusion Models?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q2_K (7.1 GB file, about 8.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (16.8 GB file, about 19.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (21.8 GB file, about 24.9 GB in use).
Which Diffusion Models quant should you choose?
Q8_0 (12.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is the first one in the table at 6.8 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Diffusion Models
How much VRAM does Diffusion Models need?
About 14.8 GB at Q8_0 with an 8K context window. That is the 12.7 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 Diffusion Models on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Diffusion Models GGUF?
It depends on the quant: file is 6.8 GB, Q4_K_S is 6.8 GB, Q2_K is 7.1 GB, Q8_0 is 12.7 GB, Q8_0 is 12.7 GB, Q8_0 is 12.7 GB and 5 more.
Where can I download Diffusion Models GGUF?
The files are on Hugging Face in the f5aiteam/Diffusion_Models repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Diffusion Models on 8 GB VRAM?
Yes, using the Q4_K_S quantization which requires about 8.1 GB of VRAM at 8k context.
What is the largest quantization I can use on 24 GB VRAM?
The Q8_0 quantization with a 21.76 GB file requires about 24.9 GB of VRAM at 8k context.
Does this model support multiple languages?
No language restrictions are listed for this model.