Krea 2 Turbo GGUF Quantizations This repository contains GGUF format quantizations of Krea 2 Turbo , a state of the art 12 billion parameter Diffusion Transformer (DiT) text to image model developed by Krea.ai. GGUF weights allow for efficient, low memory inference across consumer hardware, CPUs, and Apple Silicon. 📂 Available Files & Sizes File Name Quantization Type Size Description : : : : : : Krea 2 Turbo Q3 K M.gguf Q3 K M ~6.01 GB Highly compressed, lowest memory usage. Krea 2 Turbo Q3 K S.gguf Q3 K S ~6.01 GB Small variation of 3 bit quantization. Krea 2 Turbo Q4 K M.gguf Q4 K M ~7.49 GB Balanced medium quantization, recommended baseline. Krea 2 Turbo Q4 K S.gguf Q4 K S ~7.49 GB Small variation of 4 bit quantization. Krea 2 Turbo Q5 K M.gguf Q5 K M ~8.87 GB High quality, great balance of speed and retention. Krea 2 Turbo Q5 K S.gguf Q5 K S ~8.87 GB Small variation of 5 bit quantization. Krea 2 Turbo Q6 K.gguf Q6 K ~10.6 GB Near lossless representation of original weights. Krea 2 Turbo Q8 0.gguf Q8 0 ~13.7 GB Extremely high precision, closest to full 16 bit. 🚀 Inference Guide Using llama.cpp / stable diffusion.cpp You can run these GGUF text to image files directly using co…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy