mradermacher/Muse-Glimmer-30B-heretic-v2-GGUF
Quantization vs coder3101/Muse-Glimmer-30B-heretic-v2. mradermacher/Muse-Glimmer-30B-heretic-v2-GGUF is a GGUF quantization (Q8_0) of the same weights: 209 tensors match exactly and 418 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/209, MLP 0/156, Attention 0/260