SYLIN

Abiray

Maker · 3 entries

Everything from Abiray

NameWhat to knowPrice or memoryRanks
MiniMax H3 Image GGUFModelCommunity GGUFs of the model; smallest Q2 is 6.88 GB, text encoder GGUFs at Q4 14.6 GB and Q3 12 GB~6.9 GB
Qwen Image 2.1 GGUFModelGGUF quantizations of Qwen Image 2.1, smallest 3.19 GB, usable on about 4 GB VRAM~4 GB
LTX GGUFModelCommunity GGUF quantizations of LTX 2.5 by Abiray; smallest Q3 is 12.6 GB and produced acceptable output in test~12.6 GB