mradermacher/Qwen3-30B-A3B-abliterated-GGUF
Full fine-tune vs mlabonne/Qwen3-30B-A3B-abliterated. mradermacher/Qwen3-30B-A3B-abliterated-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 99% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 0/193, MLP 0/48, Attention 192/192, lm_head 1/1