FLUX.1 Fill dev needs about 9.8 GB of memory at Q5_0 (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 6.8 GB (Q4_0) to 23.8 GB (F16).
FLUX.1 Fill dev – 11.9B parameter image generation model
FLUX.1 Fill dev is a 11.9 billion parameter image generation model. It is available in several GGUF quantizations, compatible with ComfyUI and stable-diffusion-webui-forge. The model supports inpainting and controlnet via the quantized builds.
Good at
- Image generation
- Inpainting
- Controlnet compatibility
Limits
- No vision support in Forge as of 2024-11-21
- Large memory requirement for higher quants
- License type is other
Best for
- Generating detailed images
- Editing existing images with inpainting
- Using controlnet for guided generation
Who it’s for. Developers and artists who need a flexible, quantized image generation model that works with ComfyUI and stable-diffusion-webui-forge. The model is suitable for projects requiring inpainting or controlnet features.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 6.8 GB | 8.1 GB | Too big | Get file → | |
| Q5_0 | 8.3 GB | 9.8 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.7 GB | Too big | Get file → | |
| F16 | 23.8 GB | 27.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (6.8 GB file, 8.1 GB memory at 8 k context). For 12 GB VRAM, Q5_0 (8.28 GB file, 9.8 GB memory) is suitable. If you have 16 GB or more, Q8_0 or F16 can be used, but they require 14.7 GB and 27.2 GB memory respectively.
What GPU do you need for FLUX.1 Fill dev?
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 Q5_0 (8.3 GB file, about 9.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.7 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (23.8 GB file, about 27.2 GB in use).
Which FLUX.1 Fill dev quant should you choose?
Q5_0 (8.3 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q4_0 at 6.8 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 FLUX.1 Fill dev
How much VRAM does FLUX.1 Fill dev need?
About 9.8 GB at Q5_0 with an 8K context window. That is the 8.3 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 FLUX.1 Fill dev 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 FLUX.1 Fill dev GGUF?
It depends on the quant: Q4_0 is 6.8 GB, Q5_0 is 8.3 GB, Q8_0 is 12.7 GB, F16 is 23.8 GB.
Where can I download FLUX.1 Fill dev GGUF?
The files are on Hugging Face in the SporkySporkness/FLUX.1-Fill-dev-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 FLUX.1 Fill dev use?
Hugging Face lists the license as other. 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 FLUX.1 Fill dev on 8 GB VRAM?
Yes, the Q4_0 quant uses 8.1 GB memory at 8 k context, which fits an 8 GB VRAM setup with some headroom.
Does this model support inpainting in Forge?
Forge does not yet support Flux inpainting or controlnet as of 2024-11-21.
What are the file sizes for the available quants?
Q4_0 is 6.8 GB, Q5_0 is 8.28 GB, Q8_0 is 12.72 GB, and F16 is 23.81 GB.