matrixportalx/L3-8B-Stheno-Horny-v3.3-32K-Q4_K_S-GGUF
Quantization vs nothingiisreal/L3-8B-Stheno-Horny-v3.3-32K. matrixportalx/L3-8B-Stheno-Horny-v3.3-32K-Q4_K_S-GGUF is a GGUF quantization (Q4_K_S) of the same weights: 65 tensors match exactly and 226 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1