mradermacher/EXAONE-3.0-7.8B-Instruct-bf16-i1-GGUF
Quantization vs heegyu/EXAONE-3.0-7.8B-Instruct-bf16. mradermacher/EXAONE-3.0-7.8B-Instruct-bf16-i1-GGUF is a GGUF quantization (IQ1_M) of the same weights: 65 tensors match exactly and 226 within quantization error.
Tensors changed: Attention 0/128, Norms 0/65, MLP 0/96, Embeddings 0/1, lm_head 0/1