Ruler97/Godoter-27B
LoRA-style vs unsloth/Qwen3.6-27B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 63 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/5, MLP 192/307, Attention 64/560, lm_head 0/1, Norms 0/325, other 0/1
4 derivatives checked
- mradermacher/Godoter-27B-i1-GGUF: Quantization
- mradermacher/Godoter-27B-GGUF: Quantization
- Ruler97/Godoter-27B-GGUF: Quantization
- h1st0ry3D/Godoter-27B-MLX-4bit: Quantization
1 other repos hold byte-for-byte identical weight files.