mradermacher/trrapi-16b-GGUF
Quantization vs rizla/trrapi-16b. mradermacher/trrapi-16b-GGUF is a GGUF quantization (Q8_0) of the same weights: 142 tensors match exactly and 190 within quantization error.
Tensors changed: Embeddings 0/1, other 0/47, Norms 0/95, Attention 0/188, lm_head 0/1