QuantFactory/llama-161M-100B-GGUF
Quantization vs abacaj/llama-161M-100B. QuantFactory/llama-161M-100B-GGUF is a GGUF quantization (Q8_0) of the same weights: 25 tensors match exactly and 86 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/48