mradermacher/bagel-34b-v0.5-GGUF
Quantization vs jondurbin/bagel-34b-v0.5. mradermacher/bagel-34b-v0.5-GGUF is a GGUF quantization (Q8_0) of the same weights: 122 tensors match exactly and 421 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/121, MLP 0/180, Attention 0/240, lm_head 0/1