My primary intent of this quant is to make it run within 32 GB RAM while still having enough memory to run some of my other tasks without performance degradation. If quality is your priority and hardware is not an issue, I would recommend seeking INT8 Convrot (~14 GB) or better<hr />Experimental quantization of Kroma v0.2 by Lodestones, primarily aimed at reducing VRAM usage and improving usability on older consumer GPUs.This build uses a mixed quantization approach with INT8 tensor-wise quantization and W4A4 layers.v0.1 is kind of that sweet spot I found, not too destructive in terms of qualityv0.2 and v0.3 are further smaller is size and of course relatively lower quality v0.2 is now up and is 0.66 GB smaller compared to v0.1Used a simple T2I workflow, no second stage or upscaling done (I'm too lazy)Tested on:<ul><li>NVIDIA GTX 1660 Super 6 GB</li><li>32 GB System RAM</li></ul>Test settings:<ul><li>8 steps</li><li>CFG 1</li><li>Euler / Simple</li><li>696 × 1048 resolution</li><li>Approximately 8 s/it on a GTX 1660 Super</li></ul>This is an experimental release, so performance and compatibility may vary depending on hardware and workflow.

Kroma v0.2 Turbo INT8 Quants

Just more layers in W4A4 compared to v0.1, about 0.66 GB reduction in size. Reasonable quality loss from v0.1 as far as I can tell.Once again, too lazy for second stage or upscaling so images as is. Test settings<ul><li>8 steps</li><li>CFG 1</li><li>Euler / Simple</li><li>696 × 1048 resolution</li><li>Approximately 8 s/it on a GTX 1660 Super</li></ul>

Files with SHA256: 8c5d862232090f8d95011457de1251c3ba61b3b496438df4be7457307c48b98c