mradermacher/Omega-Evolution-31B-v4.0-GGUF
Quantization (fewer layers) vs ReadyArt/Omega-Evolution-31B-v4.0. mradermacher/Omega-Evolution-31B-v4.0-GGUF matches part of ReadyArt/Omega-Evolution-31B-v4.0 (772 of its 1188 tensors; the rest of ReadyArt/Omega-Evolution-31B-v4.0 has no counterpart). On the shared part: mradermacher/Omega-Evolution-31B-v4.0-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 411 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230