petruhonk/Qwen3.8-9B-Distill-uncensored-heretic
Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 72% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 96/211, Attention 177/336, other 0/1, Norms 58/221
9 derivatives checked
- ge525/Qwen3.8-9B-Distill-uncensored-heretic-Q4_K_M-GGUF: Quantization
- nuofang/Qwen3.8-9B-Distill-uncensored-heretic-GGUF: Not comparable yet
- Aapolon/Qwen3.5-9B-EmperoAI-Qwen3.8-Distill-Heretic-CyberStrike-GGUF: Full fine-tune
- xy10086/Qwen3.8-9B-Distill-Uncensored-Heretic-MTPLX-Q6G64: Quantization
- kataguru/Qwen3.8-9B-Distill-uncensored-heretic-Finnish-GGUF: Quantization
- Atomic-Germ/Qwen3.8-9B-Distill-uncensored-heretic-Q4_K_M-GGUF: Quantization
- disinformant/Qwen3.8-9B-Alexandria-GGUF: Full fine-tune
- 985love211/Qwen3.8-9B-Distill-uncensored-heretic-Q5_0-GGUF: Quantization
- kataguru/Qwen3.8-9B-Distill-uncensored-heretic-Finnish-W4A16-AWQ: Quantization