mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF
Quantization vs Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled. mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF is a GGUF quantization (Q8_0) of the same weights: 161 tensors match exactly and 258 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/192, Attention 0/64, Norms 0/161