mradermacher/ultiima-14b-pass1-GGUF
Quantization vs Sakalti/ultiima-14b-pass1. mradermacher/ultiima-14b-pass1-GGUF is a GGUF quantization (Q8_0) of the same weights: 421 tensors match exactly and 590 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/169, MLP 0/252, Attention 0/588