mradermacher/Pearl-34B-ties-GGUF
Quantization vs louisbrulenaudet/Pearl-34B-ties. mradermacher/Pearl-34B-ties-GGUF is a GGUF quantization (Q8_0) of the same weights: 122 tensors match exactly and 421 within quantization error.
Tensors changed: MLP 0/180, Norms 0/121, Attention 0/240, Embeddings 0/1, lm_head 0/1