mradermacher/OxytocinErosEngineering_v0.1-4x7B-passthrough-GGUF
Quantization vs weezywitasneezy/OxytocinErosEngineering_v0.1-4x7B-passthrough. mradermacher/OxytocinErosEngineering_v0.1-4x7B-passthrough-GGUF is a GGUF quantization (Q8_0) of the same weights: 257 tensors match exactly and 898 within quantization error.
Tensors changed: MLP 0/384, Norms 0/257, Attention 0/512, Embeddings 0/1, lm_head 0/1