abcdsystems/Qwen3.5-9B-Abliterated-GDN-Hybrid-EXL3-6bpw

Same weights, converted vs huihui-ai/Huihui-Qwen3.5-9B-abliterated. Same weights stored in another dtype (BF16/F32 → I16/BF16), plus 836 new tensors.

Tensors changed: Embeddings 0/5, Attention 0/228, Norms 0/221, MLP 0/112

On the Hub · Downloads on Model Pulse