sigmanih/Qwen-Qwen2.5-Coder-14B-Instruct-GGUF-Q3_K_M
Quantization vs Qwen/Qwen2.5-Coder-14B-Instruct. sigmanih/Qwen-Qwen2.5-Coder-14B-Instruct-GGUF-Q3_K_M is a GGUF quantization (Q3_K_M) of the same weights: 241 tensors match exactly and 338 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/336, lm_head 0/1