FL

FLUX.1 Fill dev

FluxGGUF by second-stateUpdated 2024-11-27
Download on Hugging Face
Parameters11.9B
Context—
Layers—
Architecture—
Smallest quant4.2 GB
Quick answer

FLUX.1 Fill dev needs about 8.3 GB of memory at Q4_K (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 4.2 GB (Q2_K) to 12.8 GB (Q8_0).

FLUX.1 Fill dev – a 11.9B parameter image inpainting model

FLUX.1 Fill dev is a 11.9B parameter model designed for image inpainting. It is available in GGUF format and can be run with llama.cpp. The model is part of the Flux family and was quantized by second‑state.

Good at

  • Image inpainting
  • High‑resolution fill
  • Contextual image editing

Limits

  • No vision support in current GGUF release
  • License is other, not open source
  • Requires 8k context for full performance

Best for

  • Restoring damaged photos
  • Adding missing elements to images
  • Creative image editing tasks

Who it’s for. Developers and researchers needing a lightweight inpainting model for local inference. It is suitable for projects that require a 11.9B parameter model without the need for external vision pipelines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.2 GB 5.2 GB
Fits Get file →
Q3_K5.4 GB 6.5 GB
Fits Get file →
Q4_06.9 GB 8.3 GB
Too big Get file →
Q4_K6.9 GB 8.3 GB
Too big Get file →
Q4_17.7 GB 9.1 GB
Too big Get file →
Q5_08.4 GB 9.9 GB
Too big Get file →
Q5_19.1 GB 10.7 GB
Too big Get file →
Q8_012.8 GB 14.9 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 4.16 GB, estimated memory 5.2 GB). For 12 GB VRAM, Q4_0 or Q4_K (file size 6.93 GB, estimated memory 8.3 GB). For 16 GB VRAM, Q5_1 (file size 9.15 GB, estimated memory 10.7 GB).

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: the best quant that fits is Q2_K (4.2 GB file, about 5.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K (5.4 GB file, about 6.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_1 (9.1 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (12.8 GB file, about 14.9 GB in use).

Which FLUX.1 Fill dev quant should you choose?

Q4_K (6.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K at 4.2 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

Parameters11.9B

Source

Quantized bysecond-state
FamilyFlux
Licenseother
Downloads (HF)2,300
Last updated2024-11-27

Frequently asked questions about FLUX.1 Fill dev

How much VRAM does FLUX.1 Fill dev need?

About 8.3 GB at Q4_K with an 8K context window. That is the 6.9 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?

Yes, with Q3_K: the 5.4 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of FLUX.1 Fill dev GGUF?

It depends on the quant: Q2_K is 4.2 GB, Q3_K is 5.4 GB, Q4_0 is 6.9 GB, Q4_K is 6.9 GB, Q4_1 is 7.7 GB, Q5_0 is 8.4 GB and 2 more.

Where can I download FLUX.1 Fill dev GGUF?

The files are on Hugging Face in the second-state/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 Q2_K quantization requires about 5.2 GB of VRAM at 8k context, which fits within an 8 GB budget.

Does the model support vision tasks?

The current GGUF release does not include vision components; it focuses on inpainting only.

What license applies to this model?

The model is licensed under an 'other' license, not open source.

Other GGUFs of FLUX.1-Fill-dev

Similar models

Browse all →

More from second-state

All by second-state →

More Flux models

All Flux →

Other medium models

All medium models →