NikolayKozloff/Qwen3-15B-A2B-Base-Q4_K_M-GGUF
Quantization vs TroyDoesAI/Qwen3-15B-A2B-Base. NikolayKozloff/Qwen3-15B-A2B-Base-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 121 tensors match exactly and 98 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/24, Attention 0/96, lm_head 0/1