mradermacher/K1-31B-v5-i1-GGUF
Quantization (fewer layers) vs win10/K1-31B-v5. mradermacher/K1-31B-v5-i1-GGUF matches part of win10/K1-31B-v5 (772 of its 1188 tensors; the rest of win10/K1-31B-v5 has no counterpart). On the shared part: mradermacher/K1-31B-v5-i1-GGUF is a GGUF quantization (Q6_K) 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