Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors
Partial fine-tune vs Qwen/Qwen3.5-35B-A3B. Partial change: 65% of the weights changed (attention, mlp), in 31 of 40 layers.
Tensors changed: MLP 153/1165, lm_head 0/1, Embeddings 0/5, Attention 27/392, other 0/1, Norms 0/247
5 derivatives checked
- mradermacher/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors-i1-GGUF: Quantization
- mradermacher/Qwen3.5-35B-A3B-Uncensored-Aggressive-safetensors-GGUF: Quantization
- Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-NVFP4: Quantization
- tthoman79/Qwen3.5-35B-A3B-Uncensored-Aggressive-mlx-4bit: Quantization
- Li101/Qwen3.5-35B-A3B-Uncensored-Aggressive-FP8: Quantization