nDimensional/Qwen3.5-9B-Uncensored-Safetensors
Same weights, converted vs HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive. Same weights stored in another dtype (BF16/F32 → BF16), plus 357 new tensors.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32
3 derivatives checked
- mradermacher/Qwen3.5-9B-Uncensored-Safetensors-i1-GGUF: Quantization
- mradermacher/Qwen3.5-9B-Uncensored-Safetensors-GGUF: Same weights, converted
- CezarJedi/Qwen3.5-9B-Abliterated-NVFP4-FP8KV: Quantization
2 other repos hold byte-for-byte identical weight files.