<h3 id="kroma">Kroma</h3>Converted from <a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/Kroma/tree/main">https://huggingface.co/lodestones/Kroma/tree/main</a>All credit belongs to the original model author. License is the same as the original model.Quantized qwen3vl text encoder: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2760440">link</a>.<hr />w4a8 xl:This version is optimized for 12GiB VRAM. The file size is ~9.2 GiB, ~40% layers are int8convrot. This ckpt should be able to fully load to the VRAM without offloading/swapping (Assuming your OS won't allocate more than 1GiB VRAM), and you get the maximum speed and better precision (Similar to GGUF XL suffix). <hr />int8convrot and others:<a target="_blank" rel="ugc" href="https://huggingface.co/Stabhappy/kroma-v0.2-base-INT8-convrot">https://huggingface.co/Stabhappy/kroma-v0.2-base-INT8-convrot</a><a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/Kroma-Quant/tree/main">https://huggingface.co/silveroxides/Kroma-Quant</a>

Files with SHA256: 7c8c815633c7f0998730c8420c99c672dfad81625b0e5dcaf62935726176e508