Model Description


language:
  • en
tags:
  • gguf
  • sd.cpp
  • stable-diffusion.cpp
  • flux
base_model:
  • black-forest-labs/FLUX.1-dev
quantized_by: leejet

FLUX gguf quantized files

The license of the quantized files follows the license of the original model:
- FLUX.1-dev: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md

These files are converted using https://github.com/leejet/stable-diffusion.cpp

Run FLUX using stable-diffusion.cpp with a GPU that has 6GB or even 4GB of VRAM: https://github.com/leejet/stable-diffusion.cpp/blob/master/docs/flux.md

GGUF File List

📁 Filename 📦 Size ⚡ Download
flux1-dev-q2_k.gguf
LFS Q2
3.87 GB Download
flux1-dev-q3_k.gguf
LFS Q3
4.99 GB Download
flux1-dev-q4_0.gguf
Recommended LFS Q4
6.45 GB Download
flux1-dev-q4_k.gguf
LFS Q4
6.45 GB Download
flux1-dev-q8_0.gguf
LFS Q8
11.96 GB Download