Quantization of inclusionAI/TwinFlow-Z-Image-Turbo. It should work if used with float64 precision.

Downloads last month
70
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for aydin99/TwinFlow-Z-Image-Turbo-SDNQ-uint4-svd-r32

Finetuned
(1)
this model