kueizen/Marco-Mini-Instruct-REAP-GGUF
Quantization vs ATH-MaaS/Marco-Mini-Instruct. kueizen/Marco-Mini-Instruct-REAP-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 113 tensors match exactly and 113 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/113, Attention 0/112