mradermacher/K1-v6-zero-GGUF
Quantization (fewer layers) vs win10/K1-v6-zero. mradermacher/K1-v6-zero-GGUF matches part of win10/K1-v6-zero (772 of its 1188 tensors; the rest of win10/K1-v6-zero has no counterpart). On the shared part: mradermacher/K1-v6-zero-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