🐹 Qwen3-30B-A3B-abliterated

Qwen3 Abliterated 0.6B • 1.7B • 4B • 8B • 14B • 30B-A3B

This model is still W.I.P. and I do not recommend using it at the moment.

This is an uncensored version of Qwen/Qwen3-30B-A3B created with a new abliteration technique. See this article to know more about abliteration.

Safetensors

Model size

30.5B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mlabonne/Qwen3-30B-A3B-abliterated

Base model

Finetuned

Finetuned

(11)

this model

Quantizations