mradermacher/Mini-Lama-14B-Base-GGUF
Quantization vs Nabbers1999/Mini-Llama-14B-Base-0124. mradermacher/Mini-Lama-14B-Base-GGUF is a GGUF quantization (Q8_0) of the same weights: 81 tensors match exactly and 280 within quantization error.
Tensors changed: Norms 0/81, MLP 0/120, Attention 0/160