nbeerbower/Qwen3.6-27B-TIES
LoRA-style vs TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/5, MLP 193/307, Attention 305/560, lm_head 0/1, Norms 0/325, other 0/1
2 derivatives checked
- mradermacher/Qwen3.6-27B-TIES-i1-GGUF: Quantization
- mradermacher/Qwen3.6-27B-TIES-GGUF: Quantization