mradermacher/Maxine-34B-stock-GGUF
Quantization vs louisbrulenaudet/Maxine-34B-stock. mradermacher/Maxine-34B-stock-GGUF is a GGUF quantization (Q8_0) of the same weights: 121 tensors match exactly and 422 within quantization error.
Tensors changed: MLP 0/180, Norms 0/121, Attention 0/240, Embeddings 0/1, lm_head 0/1