Model Gallery

1 models from 1 repositories

Filter by type:

Filter by tags:

flux.2-klein-4b-q8_0-ggml
FLUX.2 [klein] 4B is a compact, distilled text-to-image model from Black Forest Labs. It generates in 4 steps with a guidance scale of 1, uses a Qwen3 4B text encoder and the FLUX.2 VAE, and runs on a consumer GPU. This is the Q8_0 quantization of the diffusion model (~4.3 GB) by leejet for stable-diffusion.cpp, with the Qwen3 4B Q4_K_M text encoder (~2.5 GB) and the FLUX.2 VAE.

Repository: localaiLicense: apache-2.0