---

T5, Clip, and ae are still not provided in the original model

FLUX.1-Redux-dev-GGUF

Original Model

black-forest-labs/FLUX.1-Redux-dev

Run with LlamaEdge-StableDiffusion

• Version: coming soon

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
flux1-redux-dev-Q4_0.gguf	Q4_0	4	36.3 MB
flux1-redux-dev-Q4_1.gguf	Q4_1	4	40.4 MB
flux1-redux-dev-Q5_0.gguf	Q5_0	5	44.4 MB
flux1-redux-dev-Q5_1.gguf	Q5_1	5	48.4 MB
flux1-redux-dev-Q8_0.gguf	Q8_0	8	68.6 MB
flux1-redux-dev.safetensors	f16	16	129 MB

Quantized with stable-diffusion.cpp master-c3eeb669.