mradermacher/Psychosis-14B-v0-BRF-GGUF
Quantization vs Naphula/Psychosis-14B-v0-BRF. mradermacher/Psychosis-14B-v0-BRF-GGUF is a GGUF quantization (Q8_0) of the same weights: 261 tensors match exactly and 456 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/261, MLP 0/195, Attention 0/260