FLUX.2 Klein 4B 1-step RDM Q4_0 for NovelAide

This repository contains the immutable Apple Silicon installation assets used by NovelAide for epfl-vita/flux2-klein-1step-rdm.

The DiT comes from upstream revision b42d9dd041fe98a9fa6819041a7ba2c4dfd13037. NovelAide removes the released adapter-only model. tensor-name prefix and converts the BF16 weights to Q4_0 GGUF with stable-diffusion.cpp revision 22516991cbdf725e69b0b4a87e52ca16cce07c2d.

The Qwen3 text encoder, FLUX.2 small decoder, and sd-server runtime are pinned components of the NovelAide asset. The model and derived weights are released under Apache-2.0; the bundled runtime is covered by runtime/LICENSE.

Downloads last month
113
GGUF
Model size
4B params
Architecture
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for novelaide/FLUX.2-klein-4B-1step-RDM-GGUF

Quantized
(1)
this model