lyssquant/inkling-UD-Q2_K_XL-layers
Quantization (fewer layers) vs unsloth/inkling-GGUF. lyssquant/inkling-UD-Q2_K_XL-layers matches part of unsloth/inkling-GGUF (19 of its 1512 tensors; the rest of unsloth/inkling-GGUF has no counterpart). On the shared part: lyssquant/inkling-UD-Q2_K_XL-layers is a GGUF quantization (Q5_K/Q6_K) of the same weights: 11 tensors match exactly and 8 within quantization error.
Tensors changed: Norms 0/5, Attention 0/7, other 0/2, MLP 0/5