Krea 2 Turbo SDNQ Dynamic INT8

This is an int8 quantized version of krea/Krea-2-Turbo using SDNQ (SD.Next Quantization) with the dynamic option and Hadamard Rotation.

Note: You need SDNQ v0.2.0 or superior

Usage

You can find ready-to-use scripts in the diffusers-recipes repository.

Downloads last month
496
Safetensors
Model size
13B params
Tensor type
F32
BF16
I8
U8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for OzzyGT/Krea_2_Turbo_sdnq_dynamic_8bit

Base model

krea/Krea-2-Raw
Quantized
(28)
this model