mradermacher/Llama3-1B-Base-i1-GGUF
Quantization vs andrijdavid/Llama3-1B-Base. mradermacher/Llama3-1B-Base-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 7 tensors match exactly and 23 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/7, MLP 0/9, Attention 0/12