mradermacher/DeepPrep-Qwen2.5-14B-GGUF
Quantization vs DeepPrep/DeepPrep-Qwen2.5-14B. mradermacher/DeepPrep-Qwen2.5-14B-GGUF is a GGUF quantization (Q8_0) of the same weights: 241 tensors match exactly and 338 within quantization error.
Tensors changed: MLP 0/144, Norms 0/97, Attention 0/336, Embeddings 0/1, lm_head 0/1