zurichquants/Inkling-Small-UD-Q4_K_XL-layers
Quantization (fewer layers) vs unsloth/Inkling-Small-GGUF. zurichquants/Inkling-Small-UD-Q4_K_XL-layers matches part of unsloth/Inkling-Small-GGUF (19 of its 960 tensors; the rest of unsloth/Inkling-Small-GGUF has no counterpart). On the shared part: zurichquants/Inkling-Small-UD-Q4_K_XL-layers is a GGUF quantization (Q8_0/F32) of the same weights: 11 tensors match exactly and 8 within quantization error.
Tensors changed: Attention 0/7, other 0/2, MLP 0/5, Norms 0/5