πŸ“‹ Model Description


license: apache-2.0 language:
  • en
tags:
  • gguf
  • sd.cpp
  • stable-diffusion.cpp
  • flux
base_model:
  • black-forest-labs/FLUX.1-schnell
quantized_by: Green-Sky

FLUX.1-schnell quantized files for stable-diffusion.cpp

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

See https://github.com/leejet/stable-diffusion.cpp/blob/master/docs/flux.md and https://github.com/leejet/stable-diffusion.cpp/pull/356 for more info.

[!NOTE]

Quantization mixture changes happened in sd.cpp, as such, I uploaded new versions of existing quants.

q2kq3k
!image/png!image/png

πŸ“‚ GGUF File List

πŸ“ Filename πŸ“¦ Size ⚑ Download
ae-f16.gguf
Recommended LFS FP16
159.89 MB Download
clip_l-f16.gguf
LFS FP16
234.73 MB Download
clip_l-q8_0.gguf
LFS Q8
124.71 MB Download
flux1-schnell-q2_k.gguf
LFS Q2
3.83 GB Download
flux1-schnell-q3_k.gguf
LFS Q3
4.95 GB Download
flux1-schnell-q4_k.gguf
LFS Q4
6.41 GB Download
flux1-schnell-q8_0.gguf
LFS Q8
11.92 GB Download
t5xxl_q2_k.gguf
LFS Q2
1.5 GB Download
t5xxl_q3_k.gguf
LFS Q3
1.96 GB Download
t5xxl_q4_k.gguf
LFS Q4
2.56 GB Download
t5xxl_q8_0.gguf
LFS Q8
4.84 GB Download