mradermacher/Amaretto-3B-i1-GGUF
Quantization (fewer layers) vs AmarettoLabs/Amaretto-3B. mradermacher/Amaretto-3B-i1-GGUF matches part of AmarettoLabs/Amaretto-3B (236 of its 458 tensors; the rest of AmarettoLabs/Amaretto-3B has no counterpart). On the shared part: mradermacher/Amaretto-3B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 53 tensors match exactly and 183 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/53, MLP 0/78, Attention 0/104