I ran the actual TE from z-image through heretic and did the standard dataset. The model is abliterated.

heretic4bdefault

Other qwens can be interesting but not as exact as the trained encoder.

Downloads last month
2,641
GGUF
Model size
4B params
Architecture
qwen3
Hardware compatibility
Log In to view the estimation

We're not able to determine the quantization variants.

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