TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2
LoRA-style vs Qwen/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, 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 192/307, Attention 112/560, lm_head 0/1, Norms 0/325, other 0/1
9 derivatives checked
- lemuralabs/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-abliterated-OptiQ-3.7bpw-mlx: Quantization
- TeichAI/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-GGUF: Same weights, converted
- vathvathv/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-GGUF: Same weights, converted
- CoreWorxLab/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-int4-AutoRound: Quantization
- nightmedia/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-mxfp4-mlx: Quantization
- caslca/Qwen3.6-27B-Opus-Distill-OptiQ-4bit: Quantization
- lemuralabs/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-abliterated-OptiQ-4.5bpw-mlx: Quantization
- lemuralabs/Qwen3.6-27B-Claude-Opus-Reasoning-Distill-v2-abliterated-OptiQ-4bit-mlx: Quantization
- nbeerbower/Qwen3.6-27B-TIES: LoRA-style