mradermacher/Firefly-v4-i1-GGUF
Quantization (fewer layers) vs Guilherme34/Firefly-v4. mradermacher/Firefly-v4-i1-GGUF matches part of Guilherme34/Firefly-v4 (565 of its 2011 tensors; the rest of Guilherme34/Firefly-v4 has no counterpart). On the shared part: mradermacher/Firefly-v4-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 248 tensors match exactly and 317 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/247, MLP 0/105, other 0/71, Attention 0/140