mradermacher/smol_llama-220M-openhermes-i1-GGUF
Quantization vs BEE-spoke-data/smol_llama-220M-openhermes. mradermacher/smol_llama-220M-openhermes-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 21 tensors match exactly and 72 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/21, MLP 0/30, Attention 0/40