Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16
Partial fine-tune vs Qwen/Qwen3.6-35B-A3B. Partial change: 82% of the weights changed (attention, mlp), in 40 of 40 layers.
Tensors changed: Embeddings 0/1, Attention 22/280, MLP 128/280, Norms 0/131, lm_head 0/1
7 derivatives checked
- Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-4bit: Quantization
- mradermacher/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16-i1-GGUF: Quantization
- mradermacher/Qwen3.6-35B-A3B-Abliterated-Heretic-BF16-GGUF: Quantization
- Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-8bit: Quantization
- Johnblick187/Nexus-Coder-5Q3: Partial fine-tune (fewer layers)
- Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-6bit: Quantization
- jr12030408/Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-4bit: Quantization
1 other repos hold byte-for-byte identical weight files.