OBLITERATUS/Qwen3.6-27B-OBLITERATED
Partial fine-tune vs Qwen/Qwen3.6-27B. Partial change: 26% of the weights changed (attention, lm_head, mlp), in 18 of 64 layers.
Tensors changed: Embeddings 0/1, MLP 48/192, Attention 44/448, lm_head 1/1, Norms 0/209
2 derivatives checked
- mlx-community/Qwen3.6-27B-OBLITERATED-MLX-4bit: Quantization
- plunderstruck/Qwen3.6-27B-OBLITERATED-MTP-ROCmFP4-GGUF: Quantization
9 other repos hold byte-for-byte identical weight files.