mradermacher/juwel-beryl-GGUF
Quantization vs VextLabsinc/juwel-beryl. mradermacher/juwel-beryl-GGUF is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 562 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/321, MLP 0/240, Attention 0/320