jashepp/Equinox-31B-i1-MXFP4-GGUF
Quantization (fewer layers) vs LatitudeGames/Equinox-31B. jashepp/Equinox-31B-i1-MXFP4-GGUF matches part of LatitudeGames/Equinox-31B (772 of its 1188 tensors; the rest of LatitudeGames/Equinox-31B has no counterpart). On the shared part: jashepp/Equinox-31B-i1-MXFP4-GGUF is a GGUF quantization (MXFP4/Q8_0) of the same weights: 362 tensors match exactly and 410 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230