evalengine/unbound-e4b-wllama-gguf
Quantization (fewer layers) vs evalengine/unbound-e4b. evalengine/unbound-e4b-wllama-gguf matches part of evalengine/unbound-e4b (623 of its 2076 tensors; the rest of evalengine/unbound-e4b has no counterpart). On the shared part: evalengine/unbound-e4b-wllama-gguf is a GGUF quantization (Q4_K_M) of the same weights: 279 tensors match exactly and 344 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/278, MLP 0/126, other 0/85, Attention 0/132