tomdacat-ai/Buddy-E4B-v2-GGUF
Quantization (fewer layers) vs tomdacat-ai/Buddy-E4B-v2. tomdacat-ai/Buddy-E4B-v2-GGUF matches part of tomdacat-ai/Buddy-E4B-v2 (677 of its 2130 tensors; the rest of tomdacat-ai/Buddy-E4B-v2 has no counterpart). On the shared part: tomdacat-ai/Buddy-E4B-v2-GGUF is a GGUF quantization (Q8_0) of the same weights: 297 tensors match exactly and 380 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168