rodrigomt/Qwen3.5-27B-Uncensored-Aggressive

Partial fine-tune vs Qwen/Qwen3.5-27B. Partial change: 35% of the weights changed (attention, mlp, norms), in 64 of 64 layers.

Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 103/307, Attention 77/560, other 0/1, Norms 77/325

2 derivatives checked

• mradermacher/Qwen3.5-27B-Uncensored-Aggressive-i1-GGUF: Quantization
• mradermacher/Qwen3.5-27B-Uncensored-Aggressive-GGUF: Quantization

On the Hub · Downloads on Model Pulse